Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.4755. Min Act: -0.1700
Data Index: 1875673 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.4130. Min Act: -0.1700
Data Index: 8218875 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.3818. Min Act: -0.1700
Data Index: 8218874 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.3818. Min Act: -0.1700
Data Index: 3945177 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.3818. Min Act: -0.1700
Data Index: 7171203 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.3505. Min Act: -0.1700
Data Index: 8413489 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.3505. Min Act: -0.1700
Data Index: 869066 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.3193. Min Act: -0.1700
Data Index: 8477152 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.3193. Min Act: -0.1700
Data Index: 108768 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2880. Min Act: -0.1700
Data Index: 1652293 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2255. Min Act: -0.1700
Data Index: 3085506 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2568. Min Act: -0.1700
Data Index: 4695461 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2568. Min Act: -0.1700
Data Index: 7523021 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2255. Min Act: -0.1700
Data Index: 3662360 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2255. Min Act: -0.1700
Data Index: 153380 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2255. Min Act: -0.1700
Data Index: 8198471 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2255. Min Act: -0.1700
Data Index: 1812654 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.1943. Min Act: -0.1700
Data Index: 4634572 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2255. Min Act: -0.1700
Data Index: 819378 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4755. Min Range: -4.4755
Max Act: 4.2255. Min Act: -0.1700
Data Index: 5271137 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19