Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1855 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.3261. Min Act: -0.1700
Data Index: 2674837 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2949. Min Act: -0.1700
Data Index: 4858557 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.3261. Min Act: -0.1700
Data Index: 8619091 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2636. Min Act: -0.1700
Data Index: 1256964 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2949. Min Act: -0.1700
Data Index: 2686028 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2949. Min Act: -0.1700
Data Index: 1921861 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2949. Min Act: -0.1700
Data Index: 2069622 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2636. Min Act: -0.1700
Data Index: 6486741 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2324. Min Act: -0.1700
Data Index: 7833957 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2324. Min Act: -0.1700
Data Index: 3296353 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2636. Min Act: -0.1700
Data Index: 2329846 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2324. Min Act: -0.1700
Data Index: 220893 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.1699. Min Act: -0.1700
Data Index: 4338878 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2324. Min Act: -0.1700
Data Index: 8711917 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2324. Min Act: -0.1700
Data Index: 1911446 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2011. Min Act: -0.1700
Data Index: 5063293 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2011. Min Act: -0.1700
Data Index: 8519575 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2011. Min Act: -0.1700
Data Index: 2364816 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2011. Min Act: -0.1700
Data Index: 3727234 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3261. Min Range: -4.3261
Max Act: 4.2011. Min Act: -0.1700
Data Index: 7658807 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19