Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.9749. Min Act: -0.1700
Data Index: 7877001 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7562. Min Act: -0.1700
Data Index: 4533789 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.7249. Min Act: -0.1700
Data Index: 646258 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5999. Min Act: -0.1700
Data Index: 716838 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.6624. Min Act: -0.1700
Data Index: 6055423 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.6312. Min Act: -0.1700
Data Index: 2843075 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5999. Min Act: -0.1700
Data Index: 5894690 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5999. Min Act: -0.1700
Data Index: 1294463 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5999. Min Act: -0.1700
Data Index: 2501727 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5077964 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5687. Min Act: -0.1700
Data Index: 1127597 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5911260 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5374. Min Act: -0.1700
Data Index: 3976647 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5374. Min Act: -0.1700
Data Index: 2283129 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5062. Min Act: -0.1700
Data Index: 2333128 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5062. Min Act: -0.1700
Data Index: 8635531 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.5374. Min Act: -0.1700
Data Index: 2132132 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.4749. Min Act: -0.1700
Data Index: 8075475 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.4749. Min Act: -0.1700
Data Index: 2252106 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9749. Min Range: -4.9749
Max Act: 4.4749. Min Act: -0.1700
Data Index: 8729986 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19