Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.6937. Min Act: -0.1700
Data Index: 7376569 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.6624. Min Act: -0.1700
Data Index: 7633086 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.5374. Min Act: -0.1700
Data Index: 3026329 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.4437. Min Act: -0.1700
Data Index: 7376570 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.3499. Min Act: -0.1700
Data Index: 8369332 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.2874. Min Act: -0.1700
Data Index: 4208329 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.2562. Min Act: -0.1700
Data Index: 8301698 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.2562. Min Act: -0.1700
Data Index: 997567 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.2249. Min Act: -0.1700
Data Index: 8730880 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.2249. Min Act: -0.1700
Data Index: 429679 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1937. Min Act: -0.1700
Data Index: 6132233 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1937. Min Act: -0.1700
Data Index: 63027 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1624. Min Act: -0.1700
Data Index: 5376676 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1312. Min Act: -0.1700
Data Index: 4208330 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1624. Min Act: -0.1700
Data Index: 5711250 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1624. Min Act: -0.1700
Data Index: 5201670 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1312. Min Act: -0.1700
Data Index: 4410901 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1312. Min Act: -0.1700
Data Index: 6415954 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1624. Min Act: -0.1700
Data Index: 7436135 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6937. Min Range: -6.6937
Max Act: 6.1312. Min Act: -0.1700
Data Index: 8570484 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19