Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.5815. Min Act: -0.1700
Data Index: 4400935 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.5188. Min Act: -0.1700
Data Index: 6350421 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4875. Min Act: -0.1700
Data Index: 8201170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4875. Min Act: -0.1700
Data Index: 5328153 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4875. Min Act: -0.1700
Data Index: 5515962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 6565826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 458061 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4248. Min Act: -0.1700
Data Index: 8147006 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 2980624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4875. Min Act: -0.1700
Data Index: 2725375 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 7039474 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 2313293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4248. Min Act: -0.1700
Data Index: 6753723 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 2061103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1699
Data Index: 3913959 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 2038197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 2012606 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 6151992 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 4383152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5815. Min Range: -3.5815
Max Act: 3.4562. Min Act: -0.1700
Data Index: 77231 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19