Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2695 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.3235. Min Act: -0.1700
Data Index: 3133816 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.2450. Min Act: -0.1700
Data Index: 6366434 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.2293. Min Act: -0.1700
Data Index: 6254885 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.2293. Min Act: -0.1700
Data Index: 1782505 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.2136. Min Act: -0.1700
Data Index: 6750711 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1978. Min Act: -0.1700
Data Index: 7626669 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1664. Min Act: -0.1700
Data Index: 3170367 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1664. Min Act: -0.1700
Data Index: 4415296 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1506. Min Act: -0.1700
Data Index: 7626670 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1506. Min Act: -0.1700
Data Index: 1583039 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1506. Min Act: -0.1700
Data Index: 574614 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1349. Min Act: -0.1700
Data Index: 8784616 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1506. Min Act: -0.1700
Data Index: 4928424 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1034. Min Act: -0.1700
Data Index: 6602572 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1034. Min Act: -0.1700
Data Index: 2038608 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1191. Min Act: -0.1700
Data Index: 7837360 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1034. Min Act: -0.1700
Data Index: 8629670 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1034. Min Act: -0.1700
Data Index: 1673582 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.1034. Min Act: -0.1700
Data Index: 4294176 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3235. Min Range: -3.3235
Max Act: 3.0876. Min Act: -0.1700
Data Index: 7508108 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19