Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1909 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1445. Min Range: -6.1445
Max Act: 6.1445. Min Act: -0.1700
Data Index: 4699035 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1445. Min Range: -6.1445
Max Act: 6.0820. Min Act: -0.1700
Data Index: 3679450 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.9570. Min Act: -0.1700
Data Index: 3049448 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.8945. Min Act: -0.1700
Data Index: 8755511 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.8320. Min Act: -0.1700
Data Index: 7646875 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 2576176 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.7695. Min Act: -0.1700
Data Index: 1631389 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 1440065 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.7695. Min Act: -0.1700
Data Index: 3068906 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.8008. Min Act: -0.1700
Data Index: 7386926 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.7070. Min Act: -0.1700
Data Index: 1546896 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.6758. Min Act: -0.1700
Data Index: 3625188 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.7070. Min Act: -0.1700
Data Index: 186772 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.7383. Min Act: -0.1700
Data Index: 5094786 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.7383. Min Act: -0.1700
Data Index: 5044495 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.7070. Min Act: -0.1700
Data Index: 3949729 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.6445. Min Act: -0.1700
Data Index: 8805425 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.6758. Min Act: -0.1700
Data Index: 1984423 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.6445. Min Act: -0.1700
Data Index: 20702 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1445. Min Range: -6.1445
Max Act: 5.6758. Min Act: -0.1700
Data Index: 8186276 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19