Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4919 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 8748182 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.4041. Min Act: -0.1700
Data Index: 3372358 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.3416. Min Act: -0.1700
Data Index: 7869238 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.2791. Min Act: -0.1700
Data Index: 1978052 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.2791. Min Act: -0.1700
Data Index: 1070710 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.1541. Min Act: -0.1700
Data Index: 5712728 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.1541. Min Act: -0.1700
Data Index: 1031672 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.1541. Min Act: -0.1700
Data Index: 3985055 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.1541. Min Act: -0.1700
Data Index: 5318096 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.1541. Min Act: -0.1700
Data Index: 2199359 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.1541. Min Act: -0.1700
Data Index: 2074570 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0916. Min Act: -0.1700
Data Index: 3766330 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0916. Min Act: -0.1700
Data Index: 5234210 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0916. Min Act: -0.1700
Data Index: 2945689 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0916. Min Act: -0.1700
Data Index: 6236125 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0916. Min Act: -0.1700
Data Index: 5676318 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0291. Min Act: -0.1700
Data Index: 5631522 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0291. Min Act: -0.1700
Data Index: 2970199 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0291. Min Act: -0.1700
Data Index: 2678844 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6541. Min Range: -8.6541
Max Act: 8.0291. Min Act: -0.1700
Data Index: 5731816 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19