Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 457 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1258. Min Range: -7.1258
Max Act: 7.1258. Min Act: -0.1700
Data Index: 1806182 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1258. Min Range: -7.1258
Max Act: 7.0008. Min Act: -0.1700
Data Index: 8819110 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.9695. Min Act: -0.1700
Data Index: 994351 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.9070. Min Act: -0.1700
Data Index: 8714330 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.9070. Min Act: -0.1700
Data Index: 4581263 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.8133. Min Act: -0.1700
Data Index: 867920 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.7820. Min Act: -0.1700
Data Index: 70572 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.7195. Min Act: -0.1700
Data Index: 5317977 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.7195. Min Act: -0.1700
Data Index: 7123102 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.7195. Min Act: -0.1700
Data Index: 4051568 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6883. Min Act: -0.1700
Data Index: 7952983 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6883. Min Act: -0.1700
Data Index: 2572027 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6570. Min Act: -0.1700
Data Index: 7206030 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.7195. Min Act: -0.1700
Data Index: 7538469 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6570. Min Act: -0.1700
Data Index: 5664412 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6883. Min Act: -0.1700
Data Index: 4220005 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6570. Min Act: -0.1700
Data Index: 4249751 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6570. Min Act: -0.1700
Data Index: 3945124 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6570. Min Act: -0.1700
Data Index: 7719133 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1258. Min Range: -7.1258
Max Act: 6.6570. Min Act: -0.1700
Data Index: 6405275 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19