Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1020. Min Range: -10.1020
Max Act: 10.1020. Min Act: -0.1700
Data Index: 7717090 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.9770. Min Act: -0.1700
Data Index: 2308278 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.8520. Min Act: -0.1700
Data Index: 2313943 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.7895. Min Act: -0.1700
Data Index: 7858272 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.7270. Min Act: -0.1700
Data Index: 8193282 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.7270. Min Act: -0.1700
Data Index: 4243492 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.6645. Min Act: -0.1700
Data Index: 6600253 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.6020. Min Act: -0.1700
Data Index: 8402384 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.6020. Min Act: -0.1700
Data Index: 3915742 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.5395. Min Act: -0.1700
Data Index: 7690881 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.4770. Min Act: -0.1700
Data Index: 3777205 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.4770. Min Act: -0.1700
Data Index: 5244910 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.4145. Min Act: -0.1700
Data Index: 1238193 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.4145. Min Act: -0.1700
Data Index: 2401303 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.4145. Min Act: -0.1700
Data Index: 813986 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.4770. Min Act: -0.1700
Data Index: 5390561 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.3520. Min Act: -0.1700
Data Index: 7027093 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.3520. Min Act: -0.1700
Data Index: 1355327 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.3520. Min Act: -0.1700
Data Index: 459572 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1020. Min Range: -10.1020
Max Act: 9.3520. Min Act: -0.1700
Data Index: 2709848 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19