Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4997. Min Range: -8.4997
Max Act: 8.4997. Min Act: -0.1700
Data Index: 2099042 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4997. Min Range: -8.4997
Max Act: 8.2497. Min Act: -0.1700
Data Index: 5077611 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4997. Min Range: -8.4997
Max Act: 8.2497. Min Act: -0.1700
Data Index: 1927858 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4997. Min Range: -8.4997
Max Act: 8.2497. Min Act: -0.1700
Data Index: 8285345 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4997. Min Range: -8.4997
Max Act: 8.0622. Min Act: -0.1700
Data Index: 712537 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9997. Min Act: -0.1700
Data Index: 8669698 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9997. Min Act: -0.1700
Data Index: 1585920 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9997. Min Act: -0.1700
Data Index: 1585921 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9997. Min Act: -0.1700
Data Index: 3303142 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9685. Min Act: -0.1700
Data Index: 2383811 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9372. Min Act: -0.1700
Data Index: 5289444 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9060. Min Act: -0.1700
Data Index: 6540041 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9060. Min Act: -0.1700
Data Index: 8792317 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.9372. Min Act: -0.1700
Data Index: 6021393 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.8747. Min Act: -0.1700
Data Index: 6707419 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.8747. Min Act: -0.1700
Data Index: 89387 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.8122. Min Act: -0.1700
Data Index: 6118258 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.7810. Min Act: -0.1700
Data Index: 309868 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.7497. Min Act: -0.1700
Data Index: 2158348 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4997. Min Range: -8.4997
Max Act: 7.7497. Min Act: -0.1700
Data Index: 7350020 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19