Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4736 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.2026. Min Act: -0.1700
Data Index: 7078508 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1554. Min Act: -0.1700
Data Index: 32056 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1396. Min Act: -0.1700
Data Index: 541553 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1396. Min Act: -0.1700
Data Index: 7644082 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1396. Min Act: -0.1700
Data Index: 7736842 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1239. Min Act: -0.1700
Data Index: 3560648 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1396. Min Act: -0.1700
Data Index: 202487 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1239. Min Act: -0.1700
Data Index: 2538793 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.1081. Min Act: -0.1700
Data Index: 4867762 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0924. Min Act: -0.1700
Data Index: 1207262 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0924. Min Act: -0.1700
Data Index: 2446156 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0924. Min Act: -0.1700
Data Index: 2925889 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0766. Min Act: -0.1700
Data Index: 4903447 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0766. Min Act: -0.1700
Data Index: 5667140 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0766. Min Act: -0.1700
Data Index: 8816508 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0608. Min Act: -0.1700
Data Index: 1040016 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0450. Min Act: -0.1700
Data Index: 1562284 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0450. Min Act: -0.1700
Data Index: 2650710 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0450. Min Act: -0.1700
Data Index: 2952356 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2026. Min Range: -3.2026
Max Act: 3.0450. Min Act: -0.1700
Data Index: 2307425 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19