Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.5796. Min Act: -0.1700
Data Index: 4010295 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.5171. Min Act: -0.1700
Data Index: 6998684 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.4858. Min Act: -0.1700
Data Index: 2647151 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.3608. Min Act: -0.1700
Data Index: 4593219 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.3296. Min Act: -0.1700
Data Index: 6102670 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2983. Min Act: -0.1700
Data Index: 6340197 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2983. Min Act: -0.1700
Data Index: 7944520 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2983. Min Act: -0.1700
Data Index: 5419087 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2046. Min Act: -0.1700
Data Index: 3536199 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1733. Min Act: -0.1700
Data Index: 1424751 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2046. Min Act: -0.1700
Data Index: 7921561 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2046. Min Act: -0.1700
Data Index: 7680364 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2358. Min Act: -0.1700
Data Index: 7603025 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1733. Min Act: -0.1700
Data Index: 6291295 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2046. Min Act: -0.1700
Data Index: 6058881 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1421. Min Act: -0.1700
Data Index: 7128883 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1733. Min Act: -0.1700
Data Index: 4586940 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1733. Min Act: -0.1700
Data Index: 4051045 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1733. Min Act: -0.1700
Data Index: 6816314 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1733. Min Act: -0.1700
Data Index: 7998253 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19