Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.4626. Min Act: -0.1700
Data Index: 5408231 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.4626. Min Act: -0.1700
Data Index: 5881666 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.4001. Min Act: -0.1700
Data Index: 1478608 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.3064. Min Act: -0.1700
Data Index: 699438 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.2439. Min Act: -0.1700
Data Index: 8469780 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1814. Min Act: -0.1700
Data Index: 6254168 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1814. Min Act: -0.1700
Data Index: 492323 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1501. Min Act: -0.1700
Data Index: 6027129 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1501. Min Act: -0.1700
Data Index: 6265626 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1501. Min Act: -0.1700
Data Index: 1744578 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.0876. Min Act: -0.1700
Data Index: 3676427 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1189. Min Act: -0.1700
Data Index: 7007368 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1189. Min Act: -0.1700
Data Index: 6606219 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1501. Min Act: -0.1700
Data Index: 3614736 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.0876. Min Act: -0.1700
Data Index: 6606227 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.0876. Min Act: -0.1700
Data Index: 2437205 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.1189. Min Act: -0.1700
Data Index: 6265625 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.0876. Min Act: -0.1700
Data Index: 7619644 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.0563. Min Act: -0.1700
Data Index: 2971871 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4626. Min Range: -4.4626
Max Act: 4.0251. Min Act: -0.1700
Data Index: 3410574 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19