Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 885 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.7470. Min Act: -0.1700
Data Index: 5192978 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.6670. Min Act: -0.1700
Data Index: 6151731 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.6510. Min Act: -0.1700
Data Index: 4948497 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.6670. Min Act: -0.1700
Data Index: 8579809 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.6349. Min Act: -0.1700
Data Index: 6200004 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.6188. Min Act: -0.1700
Data Index: 3036834 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.6028. Min Act: -0.1700
Data Index: 6233343 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5705. Min Act: -0.1700
Data Index: 277588 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.6028. Min Act: -0.1700
Data Index: 3276868 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 3433179 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 4276313 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 6211065 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 4838713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 3418587 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 5083252 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5705. Min Act: -0.1700
Data Index: 1103050 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 4323776 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5705. Min Act: -0.1700
Data Index: 3501161 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5867. Min Act: -0.1700
Data Index: 2752514 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7470. Min Range: -2.7470
Max Act: 2.5544. Min Act: -0.1700
Data Index: 2164535 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19