Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.8075. Min Act: -0.1700
Data Index: 8126823 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.8075. Min Act: -0.1700
Data Index: 6317090 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.5885. Min Act: -0.1700
Data Index: 6317087 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.5103. Min Act: -0.1700
Data Index: 2714 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.5103. Min Act: -0.1700
Data Index: 5785447 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.5103. Min Act: -0.1700
Data Index: 2717 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.4946. Min Act: -0.1700
Data Index: 5630431 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.4476. Min Act: -0.1700
Data Index: 8710571 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.4319. Min Act: -0.1700
Data Index: 2572229 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.4319. Min Act: -0.1700
Data Index: 1290390 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.4162. Min Act: -0.1700
Data Index: 2331981 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.4006. Min Act: -0.1700
Data Index: 6257573 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3692. Min Act: -0.1700
Data Index: 6118989 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3692. Min Act: -0.1700
Data Index: 2331978 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3692. Min Act: -0.1700
Data Index: 5822838 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3692. Min Act: -0.1700
Data Index: 6304686 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3692. Min Act: -0.1700
Data Index: 2033595 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3535. Min Act: -0.1700
Data Index: 4599993 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3535. Min Act: -0.1700
Data Index: 1002111 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8075. Min Range: -3.8075
Max Act: 3.3378. Min Act: -0.1700
Data Index: 7769352 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19