Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.7737. Min Act: -0.1700
Data Index: 6799929 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.5862. Min Act: -0.1700
Data Index: 4974662 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.5549. Min Act: -0.1700
Data Index: 6623646 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.5237. Min Act: -0.1700
Data Index: 2445730 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.5237. Min Act: -0.1700
Data Index: 1507182 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4924. Min Act: -0.1700
Data Index: 5917325 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4612. Min Act: -0.1700
Data Index: 2307233 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4612. Min Act: -0.1700
Data Index: 115127 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4612. Min Act: -0.1700
Data Index: 2843349 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4299. Min Act: -0.1700
Data Index: 8388249 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4299. Min Act: -0.1700
Data Index: 4016658 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4299. Min Act: -0.1700
Data Index: 7715677 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4299. Min Act: -0.1700
Data Index: 4634218 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.3987. Min Act: -0.1700
Data Index: 3697152 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.3987. Min Act: -0.1700
Data Index: 5584906 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.3987. Min Act: -0.1700
Data Index: 2545931 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.3987. Min Act: -0.1700
Data Index: 2107474 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.4299. Min Act: -0.1700
Data Index: 2205767 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.3987. Min Act: -0.1700
Data Index: 1780397 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7737. Min Range: -5.7737
Max Act: 5.3362. Min Act: -0.1700
Data Index: 7078999 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19