Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.7582. Min Act: -0.1700
Data Index: 8392657 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.7269. Min Act: -0.1700
Data Index: 3463567 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.7269. Min Act: -0.1700
Data Index: 389923 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6957. Min Act: -0.1700
Data Index: 7464250 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6644. Min Act: -0.1700
Data Index: 613546 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6644. Min Act: -0.1700
Data Index: 4177154 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6644. Min Act: -0.1700
Data Index: 2976846 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6644. Min Act: -0.1700
Data Index: 125871 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6644. Min Act: -0.1700
Data Index: 4485114 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 198047 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 1947227 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 3219183 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 5209184 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6644. Min Act: -0.1700
Data Index: 5065025 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 4829937 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 1637196 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 355883 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 4234554 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 4136671 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7582. Min Range: -3.7582
Max Act: 3.6331. Min Act: -0.1700
Data Index: 3370745 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19