Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.5366. Min Act: -0.1700
Data Index: 595703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.4112. Min Act: -0.1700
Data Index: 869417 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.4112. Min Act: -0.1700
Data Index: 326615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.4112. Min Act: -0.1700
Data Index: 1523624 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3799. Min Act: -0.1700
Data Index: 733987 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3799. Min Act: -0.1700
Data Index: 2056812 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3799. Min Act: -0.1700
Data Index: 6991974 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3799. Min Act: -0.1700
Data Index: 7506558 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3799. Min Act: -0.1700
Data Index: 8249777 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3799. Min Act: -0.1700
Data Index: 1604756 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 6020149 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 5819081 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 562671 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 4840685 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 4439814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 4425456 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 3637272 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 3356259 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3485. Min Act: -0.1700
Data Index: 3204023 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5366. Min Range: -3.5366
Max Act: 3.3799. Min Act: -0.1700
Data Index: 3088477 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19