Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.3613. Min Act: -0.1700
Data Index: 8221830 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.3301. Min Act: -0.1700
Data Index: 741175 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.2988. Min Act: -0.1700
Data Index: 7704743 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.2676. Min Act: -0.1700
Data Index: 3398205 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.1426. Min Act: -0.1700
Data Index: 972245 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.1426. Min Act: -0.1700
Data Index: 7900264 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.0801. Min Act: -0.1700
Data Index: 4777331 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.0488. Min Act: -0.1700
Data Index: 2785020 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.0801. Min Act: -0.1700
Data Index: 8806961 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.0176. Min Act: -0.1700
Data Index: 2656605 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.0176. Min Act: -0.1700
Data Index: 3018958 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.0176. Min Act: -0.1700
Data Index: 4607006 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3613. Min Range: -7.3613
Max Act: 7.0176. Min Act: -0.1700
Data Index: 8676161 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3613. Min Range: -7.3613
Max Act: 6.9863. Min Act: -0.1700
Data Index: 4727767 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3613. Min Range: -7.3613
Max Act: 6.9863. Min Act: -0.1700
Data Index: 3979024 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3613. Min Range: -7.3613
Max Act: 6.9551. Min Act: -0.1700
Data Index: 1224567 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3613. Min Range: -7.3613
Max Act: 6.9863. Min Act: -0.1700
Data Index: 3309174 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3613. Min Range: -7.3613
Max Act: 6.9863. Min Act: -0.1700
Data Index: 6837475 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3613. Min Range: -7.3613
Max Act: 6.9551. Min Act: -0.1700
Data Index: 2789436 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3613. Min Range: -7.3613
Max Act: 6.9551. Min Act: -0.1700
Data Index: 6853269 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19