Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4280 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1205. Min Range: -11.1205
Max Act: 11.1205. Min Act: -0.1700
Data Index: 1316508 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.6830. Min Act: -0.1700
Data Index: 3503840 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.6205. Min Act: -0.1700
Data Index: 6761531 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.5580. Min Act: -0.1700
Data Index: 7081391 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.4330. Min Act: -0.1700
Data Index: 4586126 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.4330. Min Act: -0.1700
Data Index: 2591592 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.3705. Min Act: -0.1700
Data Index: 6717721 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.3705. Min Act: -0.1700
Data Index: 8532745 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.3080. Min Act: -0.1700
Data Index: 8594324 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.3080. Min Act: -0.1700
Data Index: 1989055 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.2455. Min Act: -0.1700
Data Index: 952311 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.1205. Min Act: -0.1700
Data Index: 4809504 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.1830. Min Act: -0.1700
Data Index: 163790 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.1830. Min Act: -0.1700
Data Index: 2515459 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.1205. Min Act: -0.1700
Data Index: 7886938 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.1205. Min Act: -0.1700
Data Index: 3723655 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.0580. Min Act: -0.1700
Data Index: 574601 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1205. Min Range: -11.1205
Max Act: 9.9955. Min Act: -0.1700
Data Index: 5775044 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1205. Min Range: -11.1205
Max Act: 10.0580. Min Act: -0.1700
Data Index: 5104847 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1205. Min Range: -11.1205
Max Act: 9.9955. Min Act: -0.1700
Data Index: 3368246 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19