Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0172. Min Range: -12.0172
Max Act: 12.0172. Min Act: -0.1700
Data Index: 721562 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.8297. Min Act: -0.1700
Data Index: 7789962 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.5797. Min Act: -0.1700
Data Index: 8422883 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.5172. Min Act: -0.1700
Data Index: 3156706 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.3922. Min Act: -0.1700
Data Index: 598628 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.3922. Min Act: -0.1700
Data Index: 3014699 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.3922. Min Act: -0.1700
Data Index: 8476595 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.3297. Min Act: -0.1700
Data Index: 7854790 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.2047. Min Act: -0.1700
Data Index: 939524 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.2672. Min Act: -0.1700
Data Index: 5636581 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.1422. Min Act: -0.1700
Data Index: 6059188 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.1422. Min Act: -0.1700
Data Index: 7098297 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.1422. Min Act: -0.1700
Data Index: 3302269 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.0797. Min Act: -0.1700
Data Index: 1248203 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.0172. Min Act: -0.1700
Data Index: 3137430 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.0172. Min Act: -0.1700
Data Index: 4079315 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.0172. Min Act: -0.1700
Data Index: 3194454 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0172. Min Range: -12.0172
Max Act: 10.9547. Min Act: -0.1700
Data Index: 286384 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0172. Min Range: -12.0172
Max Act: 11.0172. Min Act: -0.1700
Data Index: 3387993 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0172. Min Range: -12.0172
Max Act: 10.9547. Min Act: -0.1700
Data Index: 5438858 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19