Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.9107. Min Act: -0.1700
Data Index: 6978836 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.8795. Min Act: -0.1700
Data Index: 7493784 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.8482. Min Act: -0.1700
Data Index: 2228696 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.8170. Min Act: -0.1700
Data Index: 640212 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.7857. Min Act: -0.1700
Data Index: 8675809 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.7232. Min Act: -0.1700
Data Index: 3484518 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.7232. Min Act: -0.1700
Data Index: 966949 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.6920. Min Act: -0.1700
Data Index: 1764230 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.6920. Min Act: -0.1700
Data Index: 286651 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.5982. Min Act: -0.1700
Data Index: 5498986 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.5982. Min Act: -0.1700
Data Index: 8789351 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.5670. Min Act: -0.1700
Data Index: 6401154 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.5357. Min Act: -0.1700
Data Index: 4694140 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.5357. Min Act: -0.1700
Data Index: 7138699 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.5045. Min Act: -0.1700
Data Index: 3815142 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.4420. Min Act: -0.1700
Data Index: 966948 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.4732. Min Act: -0.1700
Data Index: 5198775 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.4732. Min Act: -0.1700
Data Index: 2530782 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.4732. Min Act: -0.1700
Data Index: 181488 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9107. Min Range: -6.9107
Max Act: 6.4420. Min Act: -0.1700
Data Index: 2434355 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19