Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4222 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0739. Min Act: -0.1700
Data Index: 2727339 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0427. Min Act: -0.1700
Data Index: 4323224 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8552. Min Act: -0.1700
Data Index: 5341165 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7927. Min Act: -0.1700
Data Index: 8076431 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7927. Min Act: -0.1700
Data Index: 4956565 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 7968050 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7302. Min Act: -0.1700
Data Index: 3847571 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7302. Min Act: -0.1700
Data Index: 1654038 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7302. Min Act: -0.1700
Data Index: 5483454 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7302. Min Act: -0.1700
Data Index: 6167037 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 7905402 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 6055927 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6677. Min Act: -0.1700
Data Index: 2876550 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 1947589 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6677. Min Act: -0.1700
Data Index: 7668759 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6989. Min Act: -0.1700
Data Index: 4987818 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6677. Min Act: -0.1700
Data Index: 1502808 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6677. Min Act: -0.1700
Data Index: 5449570 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6364. Min Act: -0.1700
Data Index: 1759754 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.6364. Min Act: -0.1700
Data Index: 5198137 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19