Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.7057. Min Act: -0.1700
Data Index: 145820 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.6744. Min Act: -0.1700
Data Index: 6282972 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.6432. Min Act: -0.1700
Data Index: 7293095 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.6119. Min Act: -0.1700
Data Index: 8623871 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.4869. Min Act: -0.1700
Data Index: 4629136 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.4244. Min Act: -0.1700
Data Index: 889045 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.3932. Min Act: -0.1700
Data Index: 3250826 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.3619. Min Act: -0.1700
Data Index: 2483725 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.3619. Min Act: -0.1700
Data Index: 2671550 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.3307. Min Act: -0.1700
Data Index: 5815056 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.3307. Min Act: -0.1700
Data Index: 858901 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.3307. Min Act: -0.1700
Data Index: 5824389 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.2682. Min Act: -0.1700
Data Index: 430036 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.2369. Min Act: -0.1700
Data Index: 3555431 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.2369. Min Act: -0.1700
Data Index: 3536552 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6130478 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6910282 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.1744. Min Act: -0.1700
Data Index: 1288212 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.1119. Min Act: -0.1700
Data Index: 3717964 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7057. Min Range: -6.7057
Max Act: 6.1119. Min Act: -0.1700
Data Index: 833589 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19