Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.2788. Min Act: -0.1700
Data Index: 630909 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.2163. Min Act: -0.1700
Data Index: 6532266 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.1538. Min Act: -0.1700
Data Index: 3018719 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.1538. Min Act: -0.1700
Data Index: 542541 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.1538. Min Act: -0.1700
Data Index: 8521269 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.1538. Min Act: -0.1700
Data Index: 5123911 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.1226. Min Act: -0.1700
Data Index: 8120700 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.1226. Min Act: -0.1700
Data Index: 6028097 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.1226. Min Act: -0.1700
Data Index: 8167023 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0913. Min Act: -0.1700
Data Index: 1731055 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0288. Min Act: -0.1700
Data Index: 7152209 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0601. Min Act: -0.1700
Data Index: 6610092 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0601. Min Act: -0.1700
Data Index: 334284 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0601. Min Act: -0.1700
Data Index: 5677542 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0288. Min Act: -0.1700
Data Index: 6602657 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0288. Min Act: -0.1700
Data Index: 1853068 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0288. Min Act: -0.1700
Data Index: 692135 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0288. Min Act: -0.1700
Data Index: 5380442 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0288. Min Act: -0.1700
Data Index: 5251228 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2788. Min Range: -5.2788
Max Act: 5.0288. Min Act: -0.1700
Data Index: 619376 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19