Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1102 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.5194. Min Act: -0.1700
Data Index: 1699443 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.5194. Min Act: -0.1700
Data Index: 29025 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.5037. Min Act: -0.1700
Data Index: 3444542 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.4724. Min Act: -0.1700
Data Index: 1265991 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.4097. Min Act: -0.1700
Data Index: 5966416 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.4097. Min Act: -0.1700
Data Index: 3571481 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.3627. Min Act: -0.1700
Data Index: 2737670 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.3313. Min Act: -0.1700
Data Index: 5418169 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.3313. Min Act: -0.1700
Data Index: 4561149 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.3470. Min Act: -0.1700
Data Index: 3275790 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.3156. Min Act: -0.1700
Data Index: 5013659 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2999. Min Act: -0.1700
Data Index: 3765693 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2842. Min Act: -0.1700
Data Index: 7698044 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2842. Min Act: -0.1700
Data Index: 1288385 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2842. Min Act: -0.1700
Data Index: 4202870 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2685. Min Act: -0.1700
Data Index: 2334475 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2685. Min Act: -0.1700
Data Index: 5448380 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2842. Min Act: -0.1700
Data Index: 4888101 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2528. Min Act: -0.1700
Data Index: 3485639 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5194. Min Range: -3.5194
Max Act: 3.2528. Min Act: -0.1700
Data Index: 3553383 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19