Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.7310. Min Act: -0.1700
Data Index: 3593268 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.5122. Min Act: -0.1700
Data Index: 729271 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4810. Min Act: -0.1700
Data Index: 2475880 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4810. Min Act: -0.1700
Data Index: 4064177 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4810. Min Act: -0.1700
Data Index: 7579072 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4810. Min Act: -0.1700
Data Index: 583202 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.4497. Min Act: -0.1700
Data Index: 3655244 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3872. Min Act: -0.1700
Data Index: 1129851 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3560. Min Act: -0.1700
Data Index: 4468392 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3560. Min Act: -0.1700
Data Index: 8183402 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2935. Min Act: -0.1700
Data Index: 489508 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.3247. Min Act: -0.1700
Data Index: 1054523 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2935. Min Act: -0.1700
Data Index: 1561050 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2622. Min Act: -0.1700
Data Index: 5973266 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2310. Min Act: -0.1700
Data Index: 344579 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2935. Min Act: -0.1700
Data Index: 7342124 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2622. Min Act: -0.1700
Data Index: 2491035 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2622. Min Act: -0.1700
Data Index: 6952852 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2622. Min Act: -0.1700
Data Index: 1928954 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7310. Min Range: -5.7310
Max Act: 5.2310. Min Act: -0.1700
Data Index: 3461910 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19