Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2368. Min Range: -7.2368
Max Act: 7.2368. Min Act: -0.1700
Data Index: 1464853 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2368. Min Range: -7.2368
Max Act: 7.1743. Min Act: -0.1700
Data Index: 3981680 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2368. Min Range: -7.2368
Max Act: 7.0493. Min Act: -0.1700
Data Index: 2178264 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2368. Min Range: -7.2368
Max Act: 7.0180. Min Act: -0.1700
Data Index: 4030387 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2368. Min Range: -7.2368
Max Act: 7.0180. Min Act: -0.1700
Data Index: 2146346 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.9555. Min Act: -0.1700
Data Index: 8551687 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.9555. Min Act: -0.1700
Data Index: 8538987 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.9243. Min Act: -0.1700
Data Index: 76905 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.8618. Min Act: -0.1700
Data Index: 8540535 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.8305. Min Act: -0.1700
Data Index: 4336471 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.8305. Min Act: -0.1700
Data Index: 6213357 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.8305. Min Act: -0.1700
Data Index: 4599665 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7993. Min Act: -0.1700
Data Index: 6124372 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7680. Min Act: -0.1700
Data Index: 3367795 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7680. Min Act: -0.1700
Data Index: 976773 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7680. Min Act: -0.1700
Data Index: 8134057 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7368. Min Act: -0.1700
Data Index: 4483211 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7368. Min Act: -0.1700
Data Index: 4126005 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7055. Min Act: -0.1700
Data Index: 8358343 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2368. Min Range: -7.2368
Max Act: 6.7368. Min Act: -0.1700
Data Index: 6180851 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19