Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3957 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.7446. Min Act: -0.1700
Data Index: 4826822 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.7759. Min Act: -0.1700
Data Index: 1738207 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.7759. Min Act: -0.1700
Data Index: 7860051 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.6196. Min Act: -0.1700
Data Index: 1762120 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5571. Min Act: -0.1700
Data Index: 612963 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5571. Min Act: -0.1700
Data Index: 3373743 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5259. Min Act: -0.1700
Data Index: 3052239 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5259. Min Act: -0.1700
Data Index: 6657297 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.5259. Min Act: -0.1700
Data Index: 1957343 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4946. Min Act: -0.1700
Data Index: 288554 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4946. Min Act: -0.1700
Data Index: 6244817 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4946. Min Act: -0.1700
Data Index: 1880575 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4634. Min Act: -0.1700
Data Index: 8532433 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4634. Min Act: -0.1700
Data Index: 5739570 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4634. Min Act: -0.1700
Data Index: 1220665 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4634. Min Act: -0.1700
Data Index: 5908150 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4321. Min Act: -0.1700
Data Index: 1597678 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.3696. Min Act: -0.1700
Data Index: 8746392 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4009. Min Act: -0.1700
Data Index: 1170633 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7759. Min Range: -4.7759
Max Act: 4.4009. Min Act: -0.1700
Data Index: 4315206 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19