Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.7943. Min Act: -0.1700
Data Index: 5815485 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.7318. Min Act: -0.1700
Data Index: 729743 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.7005. Min Act: -0.1700
Data Index: 5703235 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.7005. Min Act: -0.1700
Data Index: 5074759 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.6380. Min Act: -0.1700
Data Index: 1181847 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.6068. Min Act: -0.1700
Data Index: 355383 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.6068. Min Act: -0.1700
Data Index: 8502934 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.5755. Min Act: -0.1700
Data Index: 2689604 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.5755. Min Act: -0.1700
Data Index: 2620103 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.5443. Min Act: -0.1700
Data Index: 1682047 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.5443. Min Act: -0.1700
Data Index: 4267459 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.5130. Min Act: -0.1700
Data Index: 4665424 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.5130. Min Act: -0.1700
Data Index: 1878720 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.4818. Min Act: -0.1700
Data Index: 1733073 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.4505. Min Act: -0.1700
Data Index: 221370 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.4505. Min Act: -0.1700
Data Index: 91049 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.4193. Min Act: -0.1700
Data Index: 878160 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.4193. Min Act: -0.1700
Data Index: 881430 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.4193. Min Act: -0.1700
Data Index: 4122279 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7943. Min Range: -4.7943
Max Act: 4.4193. Min Act: -0.1700
Data Index: 2938812 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19