Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.2818. Min Act: -0.1700
Data Index: 5021582 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.2506. Min Act: -0.1700
Data Index: 2382949 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.2193. Min Act: -0.1700
Data Index: 6073950 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.1568. Min Act: -0.1700
Data Index: 2695283 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.1568. Min Act: -0.1699
Data Index: 4211233 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.1255. Min Act: -0.1700
Data Index: 8290708 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.1568. Min Act: -0.1700
Data Index: 5253080 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.1255. Min Act: -0.1700
Data Index: 5681457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0943. Min Act: -0.1700
Data Index: 8173731 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0630. Min Act: -0.1700
Data Index: 6532705 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0630. Min Act: -0.1700
Data Index: 6917534 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0943. Min Act: -0.1700
Data Index: 2929556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0630. Min Act: -0.1700
Data Index: 8630703 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0318. Min Act: -0.1700
Data Index: 3146377 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0630. Min Act: -0.1700
Data Index: 4521002 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0318. Min Act: -0.1700
Data Index: 4209148 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0318. Min Act: -0.1700
Data Index: 1289181 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0318. Min Act: -0.1700
Data Index: 3390908 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0630. Min Act: -0.1700
Data Index: 8702007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2818. Min Range: -4.2818
Max Act: 4.0318. Min Act: -0.1694
Data Index: 4303923 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19