Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2278. Min Range: -7.2278
Max Act: 7.2278. Min Act: -0.1700
Data Index: 4138420 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.9153. Min Act: -0.1700
Data Index: 8784160 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.9153. Min Act: -0.1700
Data Index: 178151 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.8528. Min Act: -0.1700
Data Index: 5773755 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.7903. Min Act: -0.1700
Data Index: 288697 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.7590. Min Act: -0.1700
Data Index: 2120289 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.7278. Min Act: -0.1700
Data Index: 5422533 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.7278. Min Act: -0.1700
Data Index: 3236655 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.7278. Min Act: -0.1700
Data Index: 6952934 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.6965. Min Act: -0.1700
Data Index: 7135470 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.6340. Min Act: -0.1700
Data Index: 803148 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5715. Min Act: -0.1700
Data Index: 4475305 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5715. Min Act: -0.1700
Data Index: 8407380 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5715. Min Act: -0.1700
Data Index: 2578799 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5715. Min Act: -0.1700
Data Index: 601524 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5403. Min Act: -0.1700
Data Index: 7038089 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.5090. Min Act: -0.1700
Data Index: 2211795 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.4778. Min Act: -0.1700
Data Index: 3264929 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.4778. Min Act: -0.1700
Data Index: 6343282 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2278. Min Range: -7.2278
Max Act: 6.4778. Min Act: -0.1700
Data Index: 908413 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19