Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0924. Min Range: -5.0924
Max Act: 5.0924. Min Act: -0.1700
Data Index: 76921 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8424. Min Act: -0.1700
Data Index: 5660685 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8736. Min Act: -0.1700
Data Index: 1896198 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8111. Min Act: -0.1700
Data Index: 1303671 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8111. Min Act: -0.1700
Data Index: 7991200 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8111. Min Act: -0.1700
Data Index: 8407453 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8111. Min Act: -0.1700
Data Index: 7533215 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7799. Min Act: -0.1700
Data Index: 2158683 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7799. Min Act: -0.1700
Data Index: 7549319 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4335366 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7799. Min Act: -0.1700
Data Index: 4935414 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7486. Min Act: -0.1700
Data Index: 593303 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7486. Min Act: -0.1700
Data Index: 4817783 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7486. Min Act: -0.1700
Data Index: 2182470 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7486. Min Act: -0.1700
Data Index: 2586081 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7174. Min Act: -0.1700
Data Index: 1452634 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7174. Min Act: -0.1700
Data Index: 8041648 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7174. Min Act: -0.1700
Data Index: 4511665 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.6861. Min Act: -0.1700
Data Index: 2414208 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7174. Min Act: -0.1700
Data Index: 2345068 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19