Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4774 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.4501. Min Act: -0.1700
Data Index: 5825137 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.3564. Min Act: -0.1700
Data Index: 6774478 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.3564. Min Act: -0.1700
Data Index: 8047095 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.3564. Min Act: -0.1700
Data Index: 8158889 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.2939. Min Act: -0.1700
Data Index: 7433669 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.2626. Min Act: -0.1700
Data Index: 1413425 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.2314. Min Act: -0.1700
Data Index: 1148950 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.2001. Min Act: -0.1700
Data Index: 2733546 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.2001. Min Act: -0.1700
Data Index: 8592422 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.2001. Min Act: -0.1700
Data Index: 3943355 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1376. Min Act: -0.1700
Data Index: 1168342 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1376. Min Act: -0.1700
Data Index: 1770459 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1376. Min Act: -0.1700
Data Index: 728140 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1064. Min Act: -0.1700
Data Index: 4415688 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1064. Min Act: -0.1700
Data Index: 7616812 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1064. Min Act: -0.1700
Data Index: 7426346 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1064. Min Act: -0.1700
Data Index: 4597943 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.1376. Min Act: -0.1700
Data Index: 2365315 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.0751. Min Act: -0.1700
Data Index: 2442920 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4501. Min Range: -5.4501
Max Act: 5.0751. Min Act: -0.1700
Data Index: 3254277 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19