Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.4121. Min Act: -0.1700
Data Index: 1944440 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.4434. Min Act: -0.1700
Data Index: 1674556 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.4434. Min Act: -0.1700
Data Index: 154844 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3809. Min Act: -0.1700
Data Index: 5101372 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3809. Min Act: -0.1700
Data Index: 3638167 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3496. Min Act: -0.1700
Data Index: 2110452 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3496. Min Act: -0.1700
Data Index: 4266858 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3809. Min Act: -0.1700
Data Index: 7406556 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3496. Min Act: -0.1700
Data Index: 2544358 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3496. Min Act: -0.1700
Data Index: 6061807 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3496. Min Act: -0.1700
Data Index: 8709695 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3184. Min Act: -0.1700
Data Index: 3068481 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.2871. Min Act: -0.1700
Data Index: 2760225 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.3184. Min Act: -0.1700
Data Index: 5211221 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.2871. Min Act: -0.1700
Data Index: 3752026 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.2871. Min Act: -0.1700
Data Index: 4792799 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.2559. Min Act: -0.1700
Data Index: 793072 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.2871. Min Act: -0.1700
Data Index: 5097092 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.2871. Min Act: -0.1700
Data Index: 4304830 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4434. Min Range: -4.4434
Max Act: 4.2559. Min Act: -0.1700
Data Index: 4531630 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19