Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 464 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0172. Min Range: -4.0172
Max Act: 4.0172. Min Act: -0.1700
Data Index: 1920989 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.9547. Min Act: -0.1700
Data Index: 1976243 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.9547. Min Act: -0.1700
Data Index: 4612275 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.9234. Min Act: -0.1700
Data Index: 1422794 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.9234. Min Act: -0.1700
Data Index: 3564862 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8609. Min Act: -0.1700
Data Index: 8340086 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8609. Min Act: -0.1700
Data Index: 1800449 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8453. Min Act: -0.1700
Data Index: 4264740 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8296. Min Act: -0.1700
Data Index: 6449626 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8453. Min Act: -0.1700
Data Index: 2319727 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8296. Min Act: -0.1700
Data Index: 7461036 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8140. Min Act: -0.1700
Data Index: 4164049 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.8140. Min Act: -0.1700
Data Index: 4663512 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.7984. Min Act: -0.1700
Data Index: 5800879 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.7827. Min Act: -0.1700
Data Index: 8661205 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.7827. Min Act: -0.1700
Data Index: 5203091 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.7671. Min Act: -0.1700
Data Index: 7157465 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.7358. Min Act: -0.1700
Data Index: 6123181 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.7358. Min Act: -0.1700
Data Index: 4392094 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0172. Min Range: -4.0172
Max Act: 3.6889. Min Act: -0.1700
Data Index: 6456841 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19