Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2957 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.4307. Min Act: -0.1696
Data Index: 6819828 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2744. Min Act: -0.1700
Data Index: 6066236 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2431. Min Act: -0.1700
Data Index: 3883856 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2744. Min Act: -0.1700
Data Index: 7451495 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2431. Min Act: -0.1700
Data Index: 5819572 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2119. Min Act: -0.1700
Data Index: 2150092 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 1895902 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 7877099 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 338995 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2119. Min Act: -0.1700
Data Index: 7496280 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 2630570 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 4457361 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.2119. Min Act: -0.1700
Data Index: 2183425 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 1571225 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 5970762 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1494. Min Act: -0.1700
Data Index: 4190870 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 5712747 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1806. Min Act: -0.1700
Data Index: 3128065 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1494. Min Act: -0.1700
Data Index: 5570173 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4307. Min Range: -4.4307
Max Act: 4.1494. Min Act: -0.1700
Data Index: 5575397 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19