Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1490 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.7940. Min Act: -0.1700
Data Index: 5488123 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6532. Min Act: -0.1700
Data Index: 7028283 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.6219. Min Act: -0.1700
Data Index: 701149 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5593. Min Act: -0.1700
Data Index: 2370832 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5906. Min Act: -0.1700
Data Index: 1156636 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5123. Min Act: -0.1700
Data Index: 4390806 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5123. Min Act: -0.1700
Data Index: 3168431 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.5280. Min Act: -0.1700
Data Index: 3140060 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4967. Min Act: -0.1700
Data Index: 1441408 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4967. Min Act: -0.1700
Data Index: 7808001 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4497. Min Act: -0.1700
Data Index: 8462043 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4654. Min Act: -0.1700
Data Index: 693630 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4810. Min Act: -0.1700
Data Index: 8109312 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4654. Min Act: -0.1700
Data Index: 7150589 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4654. Min Act: -0.1700
Data Index: 2522380 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4340. Min Act: -0.1700
Data Index: 3428558 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 4058572 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4183. Min Act: -0.1700
Data Index: 687442 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.4027. Min Act: -0.1700
Data Index: 302057 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7940. Min Range: -3.7940
Max Act: 3.3870. Min Act: -0.1700
Data Index: 1314812 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19