Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.4697. Min Act: -0.1700
Data Index: 8701945 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.4072. Min Act: -0.1700
Data Index: 719583 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.4072. Min Act: -0.1700
Data Index: 6356602 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.3134. Min Act: -0.1700
Data Index: 112936 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.2822. Min Act: -0.1700
Data Index: 1524566 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.2822. Min Act: -0.1700
Data Index: 6505497 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.2509. Min Act: -0.1700
Data Index: 3268981 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.2509. Min Act: -0.1700
Data Index: 2028873 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.2509. Min Act: -0.1700
Data Index: 3769488 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.2197. Min Act: -0.1700
Data Index: 2965591 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1884. Min Act: -0.1700
Data Index: 3054535 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.2197. Min Act: -0.1700
Data Index: 94944 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1884. Min Act: -0.1700
Data Index: 4854222 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1259. Min Act: -0.1700
Data Index: 4837840 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1572. Min Act: -0.1700
Data Index: 8164344 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1572. Min Act: -0.1700
Data Index: 5837497 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1572. Min Act: -0.1700
Data Index: 4723506 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1259. Min Act: -0.1700
Data Index: 103388 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1259. Min Act: -0.1700
Data Index: 3451158 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4697. Min Range: -5.4697
Max Act: 5.1259. Min Act: -0.1700
Data Index: 8563533 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19