Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0175. Min Range: -6.0175
Max Act: 6.0175. Min Act: -0.1700
Data Index: 412687 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0175. Min Range: -6.0175
Max Act: 6.0175. Min Act: -0.1700
Data Index: 1013865 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9862. Min Act: -0.1700
Data Index: 269381 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9550. Min Act: -0.1700
Data Index: 3685387 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9550. Min Act: -0.1700
Data Index: 7787150 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9550. Min Act: -0.1700
Data Index: 6633646 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.9237. Min Act: -0.1700
Data Index: 8108716 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8925. Min Act: -0.1700
Data Index: 5018144 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8612. Min Act: -0.1700
Data Index: 3195498 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8612. Min Act: -0.1700
Data Index: 3463729 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8300. Min Act: -0.1700
Data Index: 7016620 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8612. Min Act: -0.1700
Data Index: 2970017 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7987. Min Act: -0.1700
Data Index: 4386150 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8300. Min Act: -0.1699
Data Index: 4010210 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7987. Min Act: -0.1700
Data Index: 7989241 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.8300. Min Act: -0.1700
Data Index: 865171 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7987. Min Act: -0.1700
Data Index: 7170527 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7987. Min Act: -0.1700
Data Index: 8396194 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7987. Min Act: -0.1700
Data Index: 3463728 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0175. Min Range: -6.0175
Max Act: 5.7675. Min Act: -0.1700
Data Index: 2957806 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19