Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1306 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.9307. Min Act: -0.1700
Data Index: 1717455 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.7119. Min Act: -0.1700
Data Index: 4813116 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.6494. Min Act: -0.1700
Data Index: 5391350 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.5869. Min Act: -0.1700
Data Index: 5211871 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.5869. Min Act: -0.1700
Data Index: 1337318 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.5869. Min Act: -0.1700
Data Index: 6324602 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.5557. Min Act: -0.1700
Data Index: 2514059 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.5244. Min Act: -0.1700
Data Index: 3719893 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.4932. Min Act: -0.1700
Data Index: 8795999 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.4932. Min Act: -0.1700
Data Index: 7339930 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.4932. Min Act: -0.1700
Data Index: 2608158 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.4619. Min Act: -0.1700
Data Index: 4154257 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.3994. Min Act: -0.1700
Data Index: 3182486 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.3682. Min Act: -0.1700
Data Index: 7907101 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.3369. Min Act: -0.1700
Data Index: 1869793 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.3057. Min Act: -0.1700
Data Index: 5171448 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.3057. Min Act: -0.1700
Data Index: 4428524 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.2744. Min Act: -0.1700
Data Index: 8068065 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.2432. Min Act: -0.1700
Data Index: 2729296 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9307. Min Range: -7.9307
Max Act: 7.2432. Min Act: -0.1700
Data Index: 4973434 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19