Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4095 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.2623. Min Act: -0.1700
Data Index: 5329453 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.1686. Min Act: -0.1700
Data Index: 5208068 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.1686. Min Act: -0.1700
Data Index: 7458987 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.1061. Min Act: -0.1700
Data Index: 6258347 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.1373. Min Act: -0.1700
Data Index: 260225 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.1373. Min Act: -0.1700
Data Index: 6077430 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.1061. Min Act: -0.1700
Data Index: 7458992 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.0748. Min Act: -0.1700
Data Index: 7458997 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.1061. Min Act: -0.1700
Data Index: 1379789 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.0748. Min Act: -0.1700
Data Index: 1343736 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2623. Min Range: -7.2623
Max Act: 7.0436. Min Act: -0.1700
Data Index: 3229971 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.9186. Min Act: -0.1700
Data Index: 260226 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.9186. Min Act: -0.1700
Data Index: 7748673 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.9186. Min Act: -0.1700
Data Index: 15424 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.9498. Min Act: -0.1700
Data Index: 889468 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.8873. Min Act: -0.1700
Data Index: 7926575 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.8873. Min Act: -0.1700
Data Index: 6394821 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.8873. Min Act: -0.1700
Data Index: 1343712 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.8873. Min Act: -0.1700
Data Index: 7957679 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2623. Min Range: -7.2623
Max Act: 6.8873. Min Act: -0.1700
Data Index: 5208072 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19