Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.8206. Min Act: -0.1700
Data Index: 2888496 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.6331. Min Act: -0.1700
Data Index: 5651324 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.6644. Min Act: -0.1700
Data Index: 4263032 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.6019. Min Act: -0.1700
Data Index: 2082537 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5706. Min Act: -0.1700
Data Index: 258976 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.6019. Min Act: -0.1700
Data Index: 3822818 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5706. Min Act: -0.1700
Data Index: 3888045 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5706. Min Act: -0.1700
Data Index: 3018675 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5706. Min Act: -0.1700
Data Index: 1918722 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5081. Min Act: -0.1700
Data Index: 8621460 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5081. Min Act: -0.1700
Data Index: 2697293 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5081. Min Act: -0.1700
Data Index: 6622455 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.4769. Min Act: -0.1700
Data Index: 1403056 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5081. Min Act: -0.1700
Data Index: 2296547 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.5081. Min Act: -0.1700
Data Index: 2697292 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.4769. Min Act: -0.1700
Data Index: 6950164 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.4456. Min Act: -0.1700
Data Index: 6101474 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.4456. Min Act: -0.1700
Data Index: 6289596 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.4144. Min Act: -0.1700
Data Index: 6472916 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8206. Min Range: -5.8206
Max Act: 5.4144. Min Act: -0.1700
Data Index: 8031533 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19