Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.5925. Min Act: -0.1700
Data Index: 435666 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.5300. Min Act: -0.1700
Data Index: 296551 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.5300. Min Act: -0.1700
Data Index: 5313505 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.4988. Min Act: -0.1700
Data Index: 1544795 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.4675. Min Act: -0.1700
Data Index: 2905539 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.4050. Min Act: -0.1700
Data Index: 6920776 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3738. Min Act: -0.1700
Data Index: 2603786 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3738. Min Act: -0.1700
Data Index: 4023907 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3738. Min Act: -0.1700
Data Index: 3538850 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3738. Min Act: -0.1700
Data Index: 7813157 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3738. Min Act: -0.1700
Data Index: 5290532 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3425. Min Act: -0.1700
Data Index: 8830328 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3113. Min Act: -0.1700
Data Index: 3259222 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.2800. Min Act: -0.1700
Data Index: 1419407 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.3113. Min Act: -0.1700
Data Index: 194216 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.2800. Min Act: -0.1700
Data Index: 5015365 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.2175. Min Act: -0.1700
Data Index: 3448137 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.2488. Min Act: -0.1700
Data Index: 7929733 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.2488. Min Act: -0.1700
Data Index: 2100270 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5925. Min Range: -5.5925
Max Act: 5.2488. Min Act: -0.1700
Data Index: 1816046 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19