Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0315. Min Range: -6.0315
Max Act: 6.0315. Min Act: -0.1700
Data Index: 7825607 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.3753. Min Act: -0.1700
Data Index: 3800622 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.0940. Min Act: -0.1700
Data Index: 6695662 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.0940. Min Act: -0.1700
Data Index: 6306451 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.0003. Min Act: -0.1700
Data Index: 4505669 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.0315. Min Act: -0.1700
Data Index: 8195841 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0315. Min Range: -6.0315
Max Act: 5.0315. Min Act: -0.1700
Data Index: 7296485 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.9065. Min Act: -0.1700
Data Index: 6513398 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.7815. Min Act: -0.1700
Data Index: 7470227 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.7503. Min Act: -0.1700
Data Index: 2578554 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.7503. Min Act: -0.1700
Data Index: 6239638 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.6878. Min Act: -0.1700
Data Index: 978812 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.7503. Min Act: -0.1700
Data Index: 3769864 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.7190. Min Act: -0.1700
Data Index: 4473991 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.6878. Min Act: -0.1700
Data Index: 4132428 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.6565. Min Act: -0.1700
Data Index: 3804521 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.6878. Min Act: -0.1700
Data Index: 3227156 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.6565. Min Act: -0.1700
Data Index: 4582614 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.6565. Min Act: -0.1700
Data Index: 3205291 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0315. Min Range: -6.0315
Max Act: 4.6253. Min Act: -0.1700
Data Index: 7085924 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19