Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.6590. Min Act: -0.1700
Data Index: 2394286 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.5340. Min Act: -0.1700
Data Index: 4897725 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.4715. Min Act: -0.1700
Data Index: 4747091 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.4402. Min Act: -0.1700
Data Index: 7782278 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.3777. Min Act: -0.1700
Data Index: 538070 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.3777. Min Act: -0.1700
Data Index: 349051 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.3777. Min Act: -0.1700
Data Index: 4367175 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.3152. Min Act: -0.1700
Data Index: 3002608 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.3465. Min Act: -0.1700
Data Index: 6906800 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.3152. Min Act: -0.1700
Data Index: 3708689 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2527. Min Act: -0.1700
Data Index: 7752153 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2840. Min Act: -0.1700
Data Index: 4823446 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2527. Min Act: -0.1700
Data Index: 271155 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2527. Min Act: -0.1700
Data Index: 7302904 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2527. Min Act: -0.1700
Data Index: 7724133 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2527. Min Act: -0.1700
Data Index: 7283825 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2215. Min Act: -0.1700
Data Index: 79045 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2215. Min Act: -0.1700
Data Index: 2201627 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2215. Min Act: -0.1700
Data Index: 7893920 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6590. Min Range: -4.6590
Max Act: 4.2215. Min Act: -0.1700
Data Index: 7082709 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19