Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 910 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.4803. Min Act: -0.1700
Data Index: 3534655 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.2921. Min Act: -0.1700
Data Index: 7798731 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.2607. Min Act: -0.1700
Data Index: 3123372 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.2293. Min Act: -0.1700
Data Index: 2396561 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1978. Min Act: -0.1700
Data Index: 3493299 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1821. Min Act: -0.1700
Data Index: 8424586 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1506. Min Act: -0.1700
Data Index: 4748655 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1349. Min Act: -0.1700
Data Index: 5606484 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1191. Min Act: -0.1700
Data Index: 3321397 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1349. Min Act: -0.1700
Data Index: 8761677 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1191. Min Act: -0.1700
Data Index: 569261 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1191. Min Act: -0.1700
Data Index: 2814009 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1034. Min Act: -0.1700
Data Index: 2877818 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1034. Min Act: -0.1700
Data Index: 3150598 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.1034. Min Act: -0.1700
Data Index: 4292216 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.0876. Min Act: -0.1700
Data Index: 8508183 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.0718. Min Act: -0.1700
Data Index: 7282410 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.0718. Min Act: -0.1700
Data Index: 1709159 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.0718. Min Act: -0.1700
Data Index: 7729311 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4803. Min Range: -3.4803
Max Act: 3.0561. Min Act: -0.1700
Data Index: 8007886 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19