Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0716. Min Range: -7.0716
Max Act: 7.0716. Min Act: -0.1700
Data Index: 8094707 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.9466. Min Act: -0.1700
Data Index: 6950748 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.9153. Min Act: -0.1700
Data Index: 7523231 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.8841. Min Act: -0.1700
Data Index: 5631123 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.8841. Min Act: -0.1700
Data Index: 7229316 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.8528. Min Act: -0.1700
Data Index: 5500258 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7903. Min Act: -0.1700
Data Index: 7048259 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7903. Min Act: -0.1700
Data Index: 3192356 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7903. Min Act: -0.1700
Data Index: 4626429 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.7591. Min Act: -0.1700
Data Index: 7668643 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6653. Min Act: -0.1700
Data Index: 7052706 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6966. Min Act: -0.1700
Data Index: 939917 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6966. Min Act: -0.1700
Data Index: 231244 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6966. Min Act: -0.1700
Data Index: 6431648 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6966. Min Act: -0.1700
Data Index: 464945 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6653. Min Act: -0.1700
Data Index: 2427036 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6653. Min Act: -0.1700
Data Index: 5836806 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6653. Min Act: -0.1700
Data Index: 1082068 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6028. Min Act: -0.1700
Data Index: 8710228 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0716. Min Range: -7.0716
Max Act: 6.6028. Min Act: -0.1700
Data Index: 2007989 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19