Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 223 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.9287. Min Act: -0.1700
Data Index: 4885539 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.9287. Min Act: -0.1700
Data Index: 2522015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8975. Min Act: -0.1700
Data Index: 4137786 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8975. Min Act: -0.1700
Data Index: 7772940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8975. Min Act: -0.1700
Data Index: 2385601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8662. Min Act: -0.1700
Data Index: 5594420 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8662. Min Act: -0.1700
Data Index: 6528383 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8662. Min Act: -0.1700
Data Index: 3326516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8662. Min Act: -0.1700
Data Index: 6019084 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 4745655 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 7946605 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 6876650 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 6659475 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 1818590 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 256058 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8037. Min Act: -0.1700
Data Index: 3702415 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8037. Min Act: -0.1700
Data Index: 3756217 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8037. Min Act: -0.1700
Data Index: 4087342 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 2719398 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9287. Min Range: -3.9287
Max Act: 3.8349. Min Act: -0.1700
Data Index: 4174745 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19