Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4998 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.5156. Min Act: -0.1700
Data Index: 4480764 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.4843. Min Act: -0.1700
Data Index: 433472 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.3593. Min Act: -0.1700
Data Index: 3735523 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.3281. Min Act: -0.1700
Data Index: 1140984 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.3593. Min Act: -0.1700
Data Index: 1229112 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.2968. Min Act: -0.1700
Data Index: 6461550 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.2968. Min Act: -0.1700
Data Index: 6642637 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.2031. Min Act: -0.1700
Data Index: 1319562 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1718. Min Act: -0.1700
Data Index: 4997977 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1718. Min Act: -0.1700
Data Index: 6761535 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1718. Min Act: -0.1700
Data Index: 2460571 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1718. Min Act: -0.1700
Data Index: 5360990 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1718. Min Act: -0.1700
Data Index: 4080203 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1406. Min Act: -0.1700
Data Index: 2584987 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1406. Min Act: -0.1700
Data Index: 6129157 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1406. Min Act: -0.1700
Data Index: 4542182 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1093. Min Act: -0.1700
Data Index: 5514674 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1093. Min Act: -0.1700
Data Index: 8084612 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1093. Min Act: -0.1700
Data Index: 3617286 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5156. Min Range: -5.5156
Max Act: 5.1093. Min Act: -0.1700
Data Index: 7953808 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19