Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1454 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.5034. Min Act: -0.1700
Data Index: 2083489 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.4097. Min Act: -0.1700
Data Index: 7166451 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.4097. Min Act: -0.1700
Data Index: 2694864 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.4097. Min Act: -0.1699
Data Index: 3759519 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3784. Min Act: -0.1700
Data Index: 7867929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 7879389 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3784. Min Act: -0.1700
Data Index: 3622951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 4922848 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 4836611 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 4694819 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1699
Data Index: 4560595 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 3864455 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 306675 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3784. Min Act: -0.1700
Data Index: 1745437 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 3532124 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 1657051 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 3508166 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 3131854 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 2940748 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5034. Min Range: -4.5034
Max Act: 4.3472. Min Act: -0.1700
Data Index: 2438488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19