Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.8694. Min Range: -13.8694
Max Act: 13.8694. Min Act: -0.1700
Data Index: 1189658 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.8694. Min Range: -13.8694
Max Act: 13.6194. Min Act: -0.1700
Data Index: 3434173 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.8069. Min Act: -0.1700
Data Index: 5407999 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.5569. Min Act: -0.1700
Data Index: 908336 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.4944. Min Act: -0.1700
Data Index: 2522498 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.3069. Min Act: -0.1700
Data Index: 3881494 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.3069. Min Act: -0.1700
Data Index: 5153725 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.3069. Min Act: -0.1700
Data Index: 8788127 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.2444. Min Act: -0.1700
Data Index: 189993 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.1819. Min Act: -0.1700
Data Index: 670488 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.1819. Min Act: -0.1700
Data Index: 3689061 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.1194. Min Act: -0.1700
Data Index: 6126316 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.1194. Min Act: -0.1700
Data Index: 5490510 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.8694. Min Range: -13.8694
Max Act: 12.0569. Min Act: -0.1700
Data Index: 5832346 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.8694. Min Range: -13.8694
Max Act: 11.9944. Min Act: -0.1700
Data Index: 6428141 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.8694. Min Range: -13.8694
Max Act: 11.9319. Min Act: -0.1700
Data Index: 5035487 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.8694. Min Range: -13.8694
Max Act: 11.9319. Min Act: -0.1700
Data Index: 4488562 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.8694. Min Range: -13.8694
Max Act: 11.9319. Min Act: -0.1700
Data Index: 3633204 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.8694. Min Range: -13.8694
Max Act: 11.9319. Min Act: -0.1700
Data Index: 1931506 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.8694. Min Range: -13.8694
Max Act: 11.8694. Min Act: -0.1700
Data Index: 1479284 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19