Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3950 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.9179. Min Act: -0.1700
Data Index: 4615373 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.8867. Min Act: -0.1700
Data Index: 758033 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.8242. Min Act: -0.1700
Data Index: 6720081 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.7617. Min Act: -0.1700
Data Index: 8404008 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.7617. Min Act: -0.1700
Data Index: 8057044 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.7929. Min Act: -0.1700
Data Index: 5313496 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.7617. Min Act: -0.1700
Data Index: 8501744 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.7304. Min Act: -0.1700
Data Index: 1896837 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.7304. Min Act: -0.1700
Data Index: 5660156 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.7617. Min Act: -0.1700
Data Index: 2920070 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6992. Min Act: -0.1700
Data Index: 3872005 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6992. Min Act: -0.1700
Data Index: 3368568 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6992. Min Act: -0.1700
Data Index: 2469950 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6992. Min Act: -0.1700
Data Index: 6600482 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6992. Min Act: -0.1700
Data Index: 8335579 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6367. Min Act: -0.1700
Data Index: 3053890 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6679. Min Act: -0.1700
Data Index: 3371832 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6992. Min Act: -0.1700
Data Index: 1329689 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6679. Min Act: -0.1700
Data Index: 3156014 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9179. Min Range: -5.9179
Max Act: 5.6679. Min Act: -0.1700
Data Index: 5660154 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19