Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.5514. Min Act: -0.1700
Data Index: 6416337 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.5514. Min Act: -0.1700
Data Index: 6450436 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.4264. Min Act: -0.1700
Data Index: 6450450 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.3951. Min Act: -0.1700
Data Index: 3024119 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.3951. Min Act: -0.1700
Data Index: 3024135 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.4264. Min Act: -0.1700
Data Index: 3024123 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.3951. Min Act: -0.1700
Data Index: 3024131 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.2389. Min Act: -0.1700
Data Index: 3690474 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.2076. Min Act: -0.1700
Data Index: 3829514 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.2076. Min Act: -0.1700
Data Index: 5398594 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.2076. Min Act: -0.1700
Data Index: 1812034 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1764. Min Act: -0.1700
Data Index: 7136501 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1451. Min Act: -0.1700
Data Index: 562069 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1451. Min Act: -0.1700
Data Index: 3554517 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1451. Min Act: -0.1700
Data Index: 8580300 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1451. Min Act: -0.1700
Data Index: 191012 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1138. Min Act: -0.1700
Data Index: 4495677 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1138. Min Act: -0.1700
Data Index: 3499372 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1138. Min Act: -0.1700
Data Index: 5802246 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5514. Min Range: -4.5514
Max Act: 4.1138. Min Act: -0.1700
Data Index: 3690472 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19