Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5189 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.5965. Min Act: -0.1700
Data Index: 804659 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.5340. Min Act: -0.1700
Data Index: 4592063 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.3778. Min Act: -0.1700
Data Index: 6220904 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.2215. Min Act: -0.1700
Data Index: 2379085 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.1590. Min Act: -0.1700
Data Index: 8616601 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.0653. Min Act: -0.1700
Data Index: 7692957 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.0028. Min Act: -0.1700
Data Index: 7960079 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5965. Min Range: -7.5965
Max Act: 7.0028. Min Act: -0.1700
Data Index: 5601974 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.9715. Min Act: -0.1700
Data Index: 2400964 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.9715. Min Act: -0.1700
Data Index: 6910987 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.9090. Min Act: -0.1700
Data Index: 2642528 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.8778. Min Act: -0.1700
Data Index: 6263458 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.9090. Min Act: -0.1700
Data Index: 4709704 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.9090. Min Act: -0.1700
Data Index: 6567873 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.9090. Min Act: -0.1700
Data Index: 4818468 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.8778. Min Act: -0.1700
Data Index: 3446245 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.8153. Min Act: -0.1700
Data Index: 8189537 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.7840. Min Act: -0.1700
Data Index: 8101055 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.7528. Min Act: -0.1700
Data Index: 117520 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5965. Min Range: -7.5965
Max Act: 6.7840. Min Act: -0.1700
Data Index: 3644984 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19