Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.9399. Min Act: -0.1700
Data Index: 485540 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.5649. Min Act: -0.1700
Data Index: 4222070 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.2524. Min Act: -0.1700
Data Index: 7367492 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.1899. Min Act: -0.1700
Data Index: 6689613 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.1899. Min Act: -0.1700
Data Index: 4054748 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.0649. Min Act: -0.1700
Data Index: 1072222 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.0649. Min Act: -0.1700
Data Index: 1027111 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.0649. Min Act: -0.1700
Data Index: 8629964 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.0649. Min Act: -0.1700
Data Index: 6854044 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9399. Min Range: -8.9399
Max Act: 8.0024. Min Act: -0.1700
Data Index: 2463356 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.9399. Min Act: -0.1700
Data Index: 4647358 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.9086. Min Act: -0.1700
Data Index: 4152482 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.8774. Min Act: -0.1700
Data Index: 5078315 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.8461. Min Act: -0.1700
Data Index: 2800174 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.8149. Min Act: -0.1700
Data Index: 401435 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.8149. Min Act: -0.1700
Data Index: 7705809 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.7836. Min Act: -0.1700
Data Index: 7861480 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.7836. Min Act: -0.1700
Data Index: 2738558 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.7524. Min Act: -0.1700
Data Index: 5070559 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9399. Min Range: -8.9399
Max Act: 7.7524. Min Act: -0.1700
Data Index: 7171576 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19