Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.6545. Min Act: -0.1700
Data Index: 4108747 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4982. Min Act: -0.1700
Data Index: 7741392 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4670. Min Act: -0.1700
Data Index: 5169580 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4357. Min Act: -0.1700
Data Index: 4820016 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4045. Min Act: -0.1700
Data Index: 8029785 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4357. Min Act: -0.1700
Data Index: 6436803 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4357. Min Act: -0.1700
Data Index: 8693987 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4357. Min Act: -0.1700
Data Index: 2149996 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3732. Min Act: -0.1700
Data Index: 8443933 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3732. Min Act: -0.1700
Data Index: 5987178 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4045. Min Act: -0.1700
Data Index: 4001245 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3732. Min Act: -0.1700
Data Index: 1828859 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4045. Min Act: -0.1700
Data Index: 8105965 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.4045. Min Act: -0.1700
Data Index: 812400 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3732. Min Act: -0.1700
Data Index: 534736 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3732. Min Act: -0.1700
Data Index: 3030443 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3107. Min Act: -0.1700
Data Index: 5444778 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3419. Min Act: -0.1700
Data Index: 3836117 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3419. Min Act: -0.1700
Data Index: 8193402 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6545. Min Range: -4.6545
Max Act: 4.3419. Min Act: -0.1700
Data Index: 8395408 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19