Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 830 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2156. Min Range: -4.2156
Max Act: 4.2156. Min Act: -0.1700
Data Index: 2399368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2156. Min Range: -4.2156
Max Act: 4.0906. Min Act: -0.1700
Data Index: 5761412 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2156. Min Range: -4.2156
Max Act: 4.0281. Min Act: -0.1700
Data Index: 6658239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2156. Min Range: -4.2156
Max Act: 4.0281. Min Act: -0.1700
Data Index: 7087212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2156. Min Range: -4.2156
Max Act: 4.0281. Min Act: -0.1700
Data Index: 996499 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2156. Min Range: -4.2156
Max Act: 4.0281. Min Act: -0.1700
Data Index: 7018289 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9968. Min Act: -0.1700
Data Index: 3403273 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9655. Min Act: -0.1700
Data Index: 7998388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9655. Min Act: -0.1700
Data Index: 8800110 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9655. Min Act: -0.1700
Data Index: 3297179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9343. Min Act: -0.1700
Data Index: 6831831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9343. Min Act: -0.1700
Data Index: 3624037 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9030. Min Act: -0.1700
Data Index: 1493193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9343. Min Act: -0.1700
Data Index: 7050904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9343. Min Act: -0.1700
Data Index: 1808865 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9343. Min Act: -0.1700
Data Index: 1773952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9343. Min Act: -0.1700
Data Index: 4635577 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9030. Min Act: -0.1700
Data Index: 2235518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9030. Min Act: -0.1700
Data Index: 658406 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2156. Min Range: -4.2156
Max Act: 3.9030. Min Act: -0.1700
Data Index: 6958733 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19