Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5099. Min Range: -8.5099
Max Act: 8.5099. Min Act: -0.1700
Data Index: 1502327 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5099. Min Range: -8.5099
Max Act: 8.2599. Min Act: -0.1700
Data Index: 6744819 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5099. Min Range: -8.5099
Max Act: 8.0724. Min Act: -0.1700
Data Index: 3876317 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.9474. Min Act: -0.1700
Data Index: 1829868 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.9474. Min Act: -0.1700
Data Index: 7913204 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.9161. Min Act: -0.1700
Data Index: 3924060 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.8536. Min Act: -0.1700
Data Index: 255647 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.7911. Min Act: -0.1700
Data Index: 1819247 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.7599. Min Act: -0.1700
Data Index: 1063729 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.6661. Min Act: -0.1700
Data Index: 3590013 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.6661. Min Act: -0.1700
Data Index: 5647988 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.6349. Min Act: -0.1699
Data Index: 8161636 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.6349. Min Act: -0.1700
Data Index: 8822241 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.6036. Min Act: -0.1700
Data Index: 632671 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.6349. Min Act: -0.1700
Data Index: 3259875 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.6036. Min Act: -0.1700
Data Index: 7130370 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.5724. Min Act: -0.1700
Data Index: 7636531 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.5411. Min Act: -0.1700
Data Index: 6540702 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.5411. Min Act: -0.1700
Data Index: 5429019 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5099. Min Range: -8.5099
Max Act: 7.5099. Min Act: -0.1700
Data Index: 6406425 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19