Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1904 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.9607. Min Act: -0.1700
Data Index: 792557 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.8357. Min Act: -0.1700
Data Index: 8455276 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.6482. Min Act: -0.1700
Data Index: 4583795 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.5857. Min Act: -0.1700
Data Index: 1052945 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.5857. Min Act: -0.1700
Data Index: 8185634 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.5857. Min Act: -0.1700
Data Index: 617687 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.5232. Min Act: -0.1700
Data Index: 6164785 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.5232. Min Act: -0.1700
Data Index: 1164191 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.3982. Min Act: -0.1700
Data Index: 8393656 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.3357. Min Act: -0.1700
Data Index: 346271 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.2107. Min Act: -0.1700
Data Index: 6865192 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.2107. Min Act: -0.1700
Data Index: 4044627 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.2107. Min Act: -0.1700
Data Index: 1379403 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.1482. Min Act: -0.1700
Data Index: 7298814 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.1482. Min Act: -0.1700
Data Index: 921312 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.1482. Min Act: -0.1700
Data Index: 3284025 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.1482. Min Act: -0.1700
Data Index: 665678 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.1482. Min Act: -0.1700
Data Index: 5834971 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.0857. Min Act: -0.1700
Data Index: 5913162 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9607. Min Range: -10.9607
Max Act: 10.1482. Min Act: -0.1700
Data Index: 4323832 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19