Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2223 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.8154. Min Act: -0.1700
Data Index: 5283348 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.8154. Min Act: -0.1700
Data Index: 247790 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.7842. Min Act: -0.1700
Data Index: 1777659 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.7216. Min Act: -0.1700
Data Index: 3634260 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.7529. Min Act: -0.1700
Data Index: 344979 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.7216. Min Act: -0.1700
Data Index: 4647141 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.6277. Min Act: -0.1700
Data Index: 7415603 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.6590. Min Act: -0.1700
Data Index: 7740385 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.6590. Min Act: -0.1700
Data Index: 1791764 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.6590. Min Act: -0.1700
Data Index: 1187282 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5964. Min Act: -0.1700
Data Index: 5059090 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5964. Min Act: -0.1700
Data Index: 935574 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5651. Min Act: -0.1700
Data Index: 1908539 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5964. Min Act: -0.1700
Data Index: 5080688 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5651. Min Act: -0.1700
Data Index: 281777 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5964. Min Act: -0.1700
Data Index: 3145840 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5651. Min Act: -0.1700
Data Index: 8175542 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.6277. Min Act: -0.1700
Data Index: 3679153 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5338. Min Act: -0.1700
Data Index: 1106361 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8154. Min Range: -3.8154
Max Act: 3.5651. Min Act: -0.1700
Data Index: 4017302 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19