Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1999. Min Range: -6.1999
Max Act: 6.1999. Min Act: -0.1700
Data Index: 2831627 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1999. Min Range: -6.1999
Max Act: 6.0437. Min Act: -0.1700
Data Index: 5174318 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1999. Min Range: -6.1999
Max Act: 6.0437. Min Act: -0.1700
Data Index: 7620396 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1999. Min Range: -6.1999
Max Act: 6.0437. Min Act: -0.1700
Data Index: 4201735 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1999. Min Range: -6.1999
Max Act: 6.0124. Min Act: -0.1700
Data Index: 7279012 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.9812. Min Act: -0.1700
Data Index: 5494813 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.9812. Min Act: -0.1700
Data Index: 4506752 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8874. Min Act: -0.1700
Data Index: 4199313 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8562. Min Act: -0.1700
Data Index: 1250836 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8874. Min Act: -0.1700
Data Index: 934274 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8874. Min Act: -0.1700
Data Index: 6936901 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8562. Min Act: -0.1700
Data Index: 6440593 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8562. Min Act: -0.1700
Data Index: 4532171 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8249. Min Act: -0.1700
Data Index: 6420721 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8874. Min Act: -0.1700
Data Index: 429780 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8249. Min Act: -0.1700
Data Index: 3603821 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.7937. Min Act: -0.1700
Data Index: 6346625 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.7937. Min Act: -0.1700
Data Index: 45731 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.8249. Min Act: -0.1700
Data Index: 969982 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1999. Min Range: -6.1999
Max Act: 5.7937. Min Act: -0.1700
Data Index: 6873639 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19