Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2431. Min Range: -8.2431
Max Act: 8.2431. Min Act: -0.1700
Data Index: 5117109 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2431. Min Range: -8.2431
Max Act: 8.2431. Min Act: -0.1700
Data Index: 2405926 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2431. Min Range: -8.2431
Max Act: 8.1181. Min Act: -0.1700
Data Index: 1304391 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2431. Min Range: -8.2431
Max Act: 8.0869. Min Act: -0.1700
Data Index: 8265314 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.8681. Min Act: -0.1700
Data Index: 52435 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.8369. Min Act: -0.1700
Data Index: 8424239 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.8056. Min Act: -0.1700
Data Index: 2778322 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.7119. Min Act: -0.1700
Data Index: 719756 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.5869. Min Act: -0.1700
Data Index: 6682723 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.5869. Min Act: -0.1700
Data Index: 557981 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.5556. Min Act: -0.1700
Data Index: 2937539 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.5556. Min Act: -0.1700
Data Index: 4819136 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.5244. Min Act: -0.1700
Data Index: 2847394 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.4931. Min Act: -0.1700
Data Index: 2669392 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.4931. Min Act: -0.1700
Data Index: 4425688 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.4931. Min Act: -0.1700
Data Index: 915065 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.4619. Min Act: -0.1700
Data Index: 885228 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.3994. Min Act: -0.1700
Data Index: 6675633 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.3681. Min Act: -0.1700
Data Index: 2001149 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2431. Min Range: -8.2431
Max Act: 7.3681. Min Act: -0.1700
Data Index: 7756730 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19