Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2370 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.6390. Min Act: -0.1700
Data Index: 4092754 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.6390. Min Act: -0.1700
Data Index: 7490217 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.6077. Min Act: -0.1700
Data Index: 6970261 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.5764. Min Act: -0.1700
Data Index: 2238740 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.5295. Min Act: -0.1700
Data Index: 2872227 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.5138. Min Act: -0.1700
Data Index: 4711676 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4981. Min Act: -0.1700
Data Index: 3399224 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4668. Min Act: -0.1700
Data Index: 8303025 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4825. Min Act: -0.1700
Data Index: 2691070 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4668. Min Act: -0.1700
Data Index: 6542887 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4825. Min Act: -0.1700
Data Index: 4342141 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4511. Min Act: -0.1700
Data Index: 582588 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4511. Min Act: -0.1700
Data Index: 2355967 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4041. Min Act: -0.1700
Data Index: 27024 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4041. Min Act: -0.1700
Data Index: 896564 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4511. Min Act: -0.1700
Data Index: 6069478 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4041. Min Act: -0.1700
Data Index: 1190273 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.4041. Min Act: -0.1700
Data Index: 8789831 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.3884. Min Act: -0.1700
Data Index: 1137955 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6390. Min Range: -3.6390
Max Act: 3.3884. Min Act: -0.1700
Data Index: 3162502 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19