Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.7243. Min Act: -0.1700
Data Index: 5029867 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.5055. Min Act: -0.1700
Data Index: 479187 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.4743. Min Act: -0.1700
Data Index: 3190641 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.4118. Min Act: -0.1700
Data Index: 4146902 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.3805. Min Act: -0.1700
Data Index: 5428188 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.3805. Min Act: -0.1700
Data Index: 5335243 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.3493. Min Act: -0.1700
Data Index: 1464496 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.3180. Min Act: -0.1700
Data Index: 1914345 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.3180. Min Act: -0.1700
Data Index: 5153074 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.3180. Min Act: -0.1700
Data Index: 815426 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.3180. Min Act: -0.1700
Data Index: 6351251 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.2868. Min Act: -0.1700
Data Index: 1558797 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.2868. Min Act: -0.1700
Data Index: 7324442 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.1930. Min Act: -0.1700
Data Index: 8094402 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.2243. Min Act: -0.1700
Data Index: 6850360 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.2243. Min Act: -0.1700
Data Index: 7599492 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.2555. Min Act: -0.1700
Data Index: 8519085 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.2243. Min Act: -0.1700
Data Index: 6049314 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.1618. Min Act: -0.1700
Data Index: 7977789 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7243. Min Range: -6.7243
Max Act: 6.1618. Min Act: -0.1700
Data Index: 8708342 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19