Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.4416. Min Act: -0.1700
Data Index: 186738 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.4103. Min Act: -0.1700
Data Index: 892448 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3789. Min Act: -0.1700
Data Index: 7903932 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3789. Min Act: -0.1700
Data Index: 7561968 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 4492716 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3161. Min Act: -0.1700
Data Index: 4870305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 8354156 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 8535210 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 6693700 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 2626836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 4825611 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 7187384 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 3688063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 7331903 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 3228668 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3475. Min Act: -0.1700
Data Index: 2894515 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3161. Min Act: -0.1700
Data Index: 335901 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3161. Min Act: -0.1700
Data Index: 370449 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3161. Min Act: -0.1700
Data Index: 6758954 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4416. Min Range: -3.4416
Max Act: 3.3161. Min Act: -0.1700
Data Index: 1356793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19