Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.4217. Min Act: -0.1700
Data Index: 5597986 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.4060. Min Act: -0.1700
Data Index: 4450029 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.3904. Min Act: -0.1700
Data Index: 6436672 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.3433. Min Act: -0.1700
Data Index: 4647698 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.3276. Min Act: -0.1700
Data Index: 1699643 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.3119. Min Act: -0.1700
Data Index: 3864210 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2962. Min Act: -0.1700
Data Index: 4126002 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2491. Min Act: -0.1700
Data Index: 1034718 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2491. Min Act: -0.1700
Data Index: 7492102 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1362059 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2177. Min Act: -0.1700
Data Index: 2327785 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2334. Min Act: -0.1700
Data Index: 7015023 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1586605 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2334. Min Act: -0.1700
Data Index: 47348 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2177. Min Act: -0.1700
Data Index: 1700445 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2177. Min Act: -0.1700
Data Index: 2872291 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2177. Min Act: -0.1700
Data Index: 6411398 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2020. Min Act: -0.1700
Data Index: 6783314 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2020. Min Act: -0.1700
Data Index: 8781834 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4217. Min Range: -3.4217
Max Act: 3.2020. Min Act: -0.1700
Data Index: 5004366 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19