Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.9305. Min Act: -0.1700
Data Index: 5799961 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.9305. Min Act: -0.1700
Data Index: 6938389 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.8680. Min Act: -0.1700
Data Index: 5830915 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.8055. Min Act: -0.1700
Data Index: 7530793 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.8055. Min Act: -0.1700
Data Index: 2832941 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 1374778 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 7181425 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 3633324 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 6466409 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 2832948 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 8629613 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 7206893 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 373046 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 1187387 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6805. Min Act: -0.1700
Data Index: 644759 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6180. Min Act: -0.1700
Data Index: 5247108 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6180. Min Act: -0.1700
Data Index: 2485545 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6180. Min Act: -0.1700
Data Index: 141944 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.5867. Min Act: -0.1700
Data Index: 2243213 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9305. Min Range: -7.9305
Max Act: 7.6180. Min Act: -0.1700
Data Index: 2281004 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19