Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2365 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4712. Min Range: -9.4712
Max Act: 9.4712. Min Act: -0.1700
Data Index: 1324764 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4712. Min Range: -9.4712
Max Act: 9.0337. Min Act: -0.1700
Data Index: 5138678 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.9087. Min Act: -0.1700
Data Index: 1457032 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.8462. Min Act: -0.1700
Data Index: 1709358 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.8462. Min Act: -0.1700
Data Index: 1089305 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.8462. Min Act: -0.1700
Data Index: 4673306 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.6587. Min Act: -0.1700
Data Index: 8145356 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.7212. Min Act: -0.1700
Data Index: 2727463 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.7212. Min Act: -0.1700
Data Index: 4645891 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.7212. Min Act: -0.1700
Data Index: 2740246 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.6587. Min Act: -0.1700
Data Index: 1084641 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.6587. Min Act: -0.1700
Data Index: 1982061 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.6587. Min Act: -0.1700
Data Index: 2370706 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.5962. Min Act: -0.1700
Data Index: 3961414 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.5962. Min Act: -0.1700
Data Index: 661292 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.5337. Min Act: -0.1700
Data Index: 7681538 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.5337. Min Act: -0.1700
Data Index: 1723514 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.5337. Min Act: -0.1700
Data Index: 2740247 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.5337. Min Act: -0.1700
Data Index: 2766957 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4712. Min Range: -9.4712
Max Act: 8.5337. Min Act: -0.1700
Data Index: 5074352 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19