Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4233 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.5091. Min Act: -0.1700
Data Index: 6061650 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.3841. Min Act: -0.1700
Data Index: 1017423 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.3841. Min Act: -0.1700
Data Index: 508516 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.3216. Min Act: -0.1700
Data Index: 2983906 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.2279. Min Act: -0.1700
Data Index: 8134849 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1966. Min Act: -0.1700
Data Index: 2529101 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1653. Min Act: -0.1700
Data Index: 4662990 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1341. Min Act: -0.1700
Data Index: 7745933 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1966. Min Act: -0.1700
Data Index: 184216 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1653. Min Act: -0.1700
Data Index: 4213782 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1653. Min Act: -0.1700
Data Index: 5318122 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1341. Min Act: -0.1700
Data Index: 6387437 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1028. Min Act: -0.1700
Data Index: 4576013 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1653. Min Act: -0.1700
Data Index: 6744089 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1341. Min Act: -0.1700
Data Index: 31520 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1341. Min Act: -0.1700
Data Index: 5148684 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1653. Min Act: -0.1700
Data Index: 6987511 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1653. Min Act: -0.1700
Data Index: 7530215 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1341. Min Act: -0.1700
Data Index: 5215726 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5091. Min Range: -4.5091
Max Act: 4.1341. Min Act: -0.1700
Data Index: 7348150 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19