Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2087 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.7133. Min Act: -0.1700
Data Index: 657080 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.6196. Min Act: -0.1700
Data Index: 3453560 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5883. Min Act: -0.1700
Data Index: 7815645 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5571. Min Act: -0.1700
Data Index: 8233715 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5571. Min Act: -0.1700
Data Index: 4303651 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 3082249 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4946. Min Act: -0.1700
Data Index: 2190187 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4946. Min Act: -0.1700
Data Index: 8016521 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 4291945 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4946. Min Act: -0.1700
Data Index: 994165 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4946. Min Act: -0.1700
Data Index: 100263 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 4674862 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 4721466 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 3086906 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 5195893 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 2575500 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 7907340 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4321. Min Act: -0.1700
Data Index: 3044879 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.3696. Min Act: -0.1700
Data Index: 5048647 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 7650325 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19