Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.4016. Min Act: -0.1700
Data Index: 3359291 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3078. Min Act: -0.1700
Data Index: 3359293 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3391. Min Act: -0.1700
Data Index: 3359307 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3078. Min Act: -0.1700
Data Index: 3359299 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3078. Min Act: -0.1700
Data Index: 3359298 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2766. Min Act: -0.1700
Data Index: 3359300 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 2546415 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 6793380 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 3359302 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1203. Min Act: -0.1700
Data Index: 3359290 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1203. Min Act: -0.1700
Data Index: 4197737 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1203. Min Act: -0.1700
Data Index: 3421712 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0578. Min Act: -0.1700
Data Index: 5415760 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0578. Min Act: -0.1700
Data Index: 3359313 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0578. Min Act: -0.1700
Data Index: 7232328 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0266. Min Act: -0.1700
Data Index: 5415761 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0266. Min Act: -0.1700
Data Index: 518099 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9953. Min Act: -0.1700
Data Index: 3359306 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9641. Min Act: -0.1700
Data Index: 578440 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9641. Min Act: -0.1700
Data Index: 3806959 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19