Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.7444. Min Act: -0.1700
Data Index: 4372054 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.7444. Min Act: -0.1700
Data Index: 2539240 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.5569. Min Act: -0.1700
Data Index: 1450028 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.5256. Min Act: -0.1700
Data Index: 3713253 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.5256. Min Act: -0.1700
Data Index: 6628866 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.5256. Min Act: -0.1700
Data Index: 6951370 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.5256. Min Act: -0.1700
Data Index: 914874 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4944. Min Act: -0.1700
Data Index: 5466671 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4631. Min Act: -0.1700
Data Index: 728127 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4944. Min Act: -0.1700
Data Index: 8433470 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4631. Min Act: -0.1700
Data Index: 3915882 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4319. Min Act: -0.1700
Data Index: 7188120 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4631. Min Act: -0.1700
Data Index: 815204 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4631. Min Act: -0.1700
Data Index: 4162128 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4006. Min Act: -0.1700
Data Index: 2522458 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4631. Min Act: -0.1700
Data Index: 7188119 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4319. Min Act: -0.1700
Data Index: 4292071 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4006. Min Act: -0.1700
Data Index: 4116669 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4319. Min Act: -0.1700
Data Index: 6438693 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7444. Min Range: -4.7444
Max Act: 4.4006. Min Act: -0.1700
Data Index: 142014 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19