Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0240. Min Range: -4.0240
Max Act: 4.0240. Min Act: -0.1700
Data Index: 3214857 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.9928. Min Act: -0.1700
Data Index: 3076521 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.9928. Min Act: -0.1700
Data Index: 5211777 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.9928. Min Act: -0.1700
Data Index: 426383 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.9928. Min Act: -0.1700
Data Index: 2112124 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.9928. Min Act: -0.1700
Data Index: 6099430 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.9928. Min Act: -0.1700
Data Index: 2322345 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8990. Min Act: -0.1700
Data Index: 1553877 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8990. Min Act: -0.1700
Data Index: 313458 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8990. Min Act: -0.1700
Data Index: 635816 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8365. Min Act: -0.1700
Data Index: 2204324 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8677. Min Act: -0.1700
Data Index: 4809777 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8677. Min Act: -0.1700
Data Index: 3892824 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8365. Min Act: -0.1700
Data Index: 7674518 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8052. Min Act: -0.1700
Data Index: 8414012 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8052. Min Act: -0.1700
Data Index: 4887569 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8052. Min Act: -0.1700
Data Index: 795093 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8052. Min Act: -0.1700
Data Index: 6416038 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.8052. Min Act: -0.1700
Data Index: 990518 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0240. Min Range: -4.0240
Max Act: 3.7895. Min Act: -0.1700
Data Index: 7044960 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19