Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.6958. Min Act: -0.1700
Data Index: 8827538 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.5396. Min Act: -0.1700
Data Index: 4980626 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.5083. Min Act: -0.1700
Data Index: 1573841 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.5083. Min Act: -0.1700
Data Index: 1879505 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.4771. Min Act: -0.1700
Data Index: 1281109 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.5083. Min Act: -0.1700
Data Index: 2803628 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.4146. Min Act: -0.1700
Data Index: 1508917 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.4146. Min Act: -0.1700
Data Index: 6476979 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.4146. Min Act: -0.1700
Data Index: 2873766 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3833. Min Act: -0.1700
Data Index: 2803625 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3833. Min Act: -0.1700
Data Index: 2867233 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3833. Min Act: -0.1700
Data Index: 7927528 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3833. Min Act: -0.1700
Data Index: 8212116 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3521. Min Act: -0.1700
Data Index: 5195316 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3208. Min Act: -0.1700
Data Index: 4236705 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3208. Min Act: -0.1700
Data Index: 4235286 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.3208. Min Act: -0.1700
Data Index: 7757166 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.2896. Min Act: -0.1700
Data Index: 2992357 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.2583. Min Act: -0.1700
Data Index: 5954348 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6958. Min Range: -6.6958
Max Act: 6.2583. Min Act: -0.1700
Data Index: 1105603 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19