Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3320 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.8675. Min Act: -0.1700
Data Index: 6950488 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.7738. Min Act: -0.1700
Data Index: 3022524 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.7425. Min Act: -0.1700
Data Index: 3926838 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.5550. Min Act: -0.1700
Data Index: 3941552 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.6175. Min Act: -0.1700
Data Index: 218388 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.5863. Min Act: -0.1700
Data Index: 5419549 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.5550. Min Act: -0.1700
Data Index: 5092922 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.4925. Min Act: -0.1700
Data Index: 1771194 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.5238. Min Act: -0.1700
Data Index: 7128315 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.4613. Min Act: -0.1700
Data Index: 6023776 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.4613. Min Act: -0.1700
Data Index: 4223094 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.3988. Min Act: -0.1700
Data Index: 4760376 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.3988. Min Act: -0.1700
Data Index: 2420243 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.3988. Min Act: -0.1700
Data Index: 355490 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.3988. Min Act: -0.1700
Data Index: 7063420 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.2738. Min Act: -0.1700
Data Index: 7564682 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.2738. Min Act: -0.1700
Data Index: 8108112 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.2425. Min Act: -0.1700
Data Index: 64 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.2113. Min Act: -0.1700
Data Index: 544169 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8675. Min Range: -6.8675
Max Act: 6.2113. Min Act: -0.1700
Data Index: 3237083 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19