Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.8715. Min Act: -0.1700
Data Index: 5206186 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.7778. Min Act: -0.1700
Data Index: 3399589 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.7153. Min Act: -0.1700
Data Index: 3600361 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.7153. Min Act: -0.1700
Data Index: 6048819 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.6215. Min Act: -0.1700
Data Index: 134770 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.5903. Min Act: -0.1700
Data Index: 6496785 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.5590. Min Act: -0.1700
Data Index: 6995687 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.5278. Min Act: -0.1700
Data Index: 1715729 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.4965. Min Act: -0.1700
Data Index: 6420939 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.4653. Min Act: -0.1700
Data Index: 8657159 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.4965. Min Act: -0.1700
Data Index: 6531973 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.4653. Min Act: -0.1700
Data Index: 2894148 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.4653. Min Act: -0.1700
Data Index: 8764010 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.4028. Min Act: -0.1700
Data Index: 4449281 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.4340. Min Act: -0.1700
Data Index: 3267911 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.3715. Min Act: -0.1700
Data Index: 3996620 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.3715. Min Act: -0.1700
Data Index: 1393422 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.3715. Min Act: -0.1700
Data Index: 6924297 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.3090. Min Act: -0.1700
Data Index: 5933350 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8715. Min Range: -6.8715
Max Act: 6.3403. Min Act: -0.1700
Data Index: 7508180 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19