Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2329 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3068. Min Range: -8.3068
Max Act: 8.3068. Min Act: -0.1700
Data Index: 245897 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3068. Min Range: -8.3068
Max Act: 8.1818. Min Act: -0.1700
Data Index: 2552586 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3068. Min Range: -8.3068
Max Act: 8.1193. Min Act: -0.1700
Data Index: 2316702 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.9943. Min Act: -0.1700
Data Index: 190737 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.9943. Min Act: -0.1700
Data Index: 1061210 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.9318. Min Act: -0.1700
Data Index: 2080721 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.9318. Min Act: -0.1700
Data Index: 609906 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.9318. Min Act: -0.1700
Data Index: 3883231 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.9318. Min Act: -0.1700
Data Index: 2259928 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.8068. Min Act: -0.1700
Data Index: 7903501 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.8068. Min Act: -0.1700
Data Index: 2818445 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.8068. Min Act: -0.1700
Data Index: 2751853 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.8068. Min Act: -0.1700
Data Index: 214342 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.7443. Min Act: -0.1700
Data Index: 2818446 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.7443. Min Act: -0.1700
Data Index: 8510339 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.7443. Min Act: -0.1700
Data Index: 975901 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.7443. Min Act: -0.1700
Data Index: 6643918 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.7443. Min Act: -0.1700
Data Index: 2383420 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.7443. Min Act: -0.1700
Data Index: 2096524 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3068. Min Range: -8.3068
Max Act: 7.6818. Min Act: -0.1700
Data Index: 315253 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19