Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4073 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.8623. Min Act: -0.1700
Data Index: 1069657 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.7998. Min Act: -0.1700
Data Index: 384986 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.7372. Min Act: -0.1700
Data Index: 6691174 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.7372. Min Act: -0.1700
Data Index: 1339348 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.7060. Min Act: -0.1700
Data Index: 2311713 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.6747. Min Act: -0.1700
Data Index: 821712 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.6747. Min Act: -0.1700
Data Index: 680161 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.6747. Min Act: -0.1700
Data Index: 4937762 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.6121. Min Act: -0.1700
Data Index: 5360557 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.6121. Min Act: -0.1700
Data Index: 500465 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5808. Min Act: -0.1700
Data Index: 3766823 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5964. Min Act: -0.1700
Data Index: 5130255 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5964. Min Act: -0.1700
Data Index: 3050219 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5964. Min Act: -0.1700
Data Index: 2862325 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5964. Min Act: -0.1700
Data Index: 419827 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5808. Min Act: -0.1700
Data Index: 659890 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5808. Min Act: -0.1700
Data Index: 2265065 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5964. Min Act: -0.1700
Data Index: 2609920 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5338. Min Act: -0.1700
Data Index: 3175965 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8623. Min Range: -3.8623
Max Act: 3.5495. Min Act: -0.1700
Data Index: 7718067 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19