Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.6464. Min Act: -0.1700
Data Index: 1912153 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.6464. Min Act: -0.1700
Data Index: 1269565 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.5526. Min Act: -0.1700
Data Index: 4586742 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.5526. Min Act: -0.1700
Data Index: 6310262 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.5214. Min Act: -0.1700
Data Index: 8486415 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.4589. Min Act: -0.1700
Data Index: 2731091 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.4276. Min Act: -0.1700
Data Index: 3771578 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.3651. Min Act: -0.1700
Data Index: 6796820 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.3651. Min Act: -0.1700
Data Index: 3089503 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.3339. Min Act: -0.1700
Data Index: 6315001 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.3339. Min Act: -0.1700
Data Index: 1545216 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.3026. Min Act: -0.1700
Data Index: 6020738 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.2714. Min Act: -0.1700
Data Index: 8607613 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.2089. Min Act: -0.1700
Data Index: 3472270 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.1776. Min Act: -0.1700
Data Index: 4021920 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.1776. Min Act: -0.1700
Data Index: 6289242 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.1776. Min Act: -0.1700
Data Index: 5190321 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.1464. Min Act: -0.1700
Data Index: 1919359 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.1464. Min Act: -0.1700
Data Index: 4034964 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6464. Min Range: -7.6464
Max Act: 7.1151. Min Act: -0.1700
Data Index: 338806 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19