Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1176 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0193. Min Range: -7.0193
Max Act: 7.0193. Min Act: -0.1700
Data Index: 7058151 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.5505. Min Act: -0.1700
Data Index: 2410787 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.5193. Min Act: -0.1700
Data Index: 7987425 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.4568. Min Act: -0.1700
Data Index: 1525870 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.3005. Min Act: -0.1700
Data Index: 458310 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.2068. Min Act: -0.1700
Data Index: 1956682 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1755. Min Act: -0.1700
Data Index: 7164331 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1443. Min Act: -0.1700
Data Index: 570149 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1443. Min Act: -0.1700
Data Index: 3882242 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1443. Min Act: -0.1700
Data Index: 6652599 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1443. Min Act: -0.1700
Data Index: 5918519 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1130. Min Act: -0.1700
Data Index: 3026249 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1130. Min Act: -0.1700
Data Index: 3437321 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.1130. Min Act: -0.1700
Data Index: 5419747 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.0818. Min Act: -0.1700
Data Index: 4651823 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.0818. Min Act: -0.1700
Data Index: 8016326 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.0818. Min Act: -0.1700
Data Index: 5242575 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.0193. Min Act: -0.1700
Data Index: 3579675 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.0505. Min Act: -0.1700
Data Index: 5841114 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0193. Min Range: -7.0193
Max Act: 6.0505. Min Act: -0.1700
Data Index: 2151249 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19