Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 940 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.8179. Min Act: -0.1688
Data Index: 537628 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.8179. Min Act: -0.1674
Data Index: 2712147 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.6797. Min Act: -0.1678
Data Index: 1568662 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.6449. Min Act: -0.1662
Data Index: 7316637 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.6275. Min Act: -0.1612
Data Index: 7178747 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5926. Min Act: -0.1699
Data Index: 1321475 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5926. Min Act: -0.1656
Data Index: 2616706 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5751. Min Act: -0.1693
Data Index: 4545206 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5926. Min Act: -0.1675
Data Index: 3842953 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5751. Min Act: -0.1393
Data Index: 1451856 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5751. Min Act: -0.1699
Data Index: 2102046 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5751. Min Act: -0.1700
Data Index: 715181 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5751. Min Act: -0.1468
Data Index: 3876343 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5401. Min Act: -0.1654
Data Index: 1173741 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5576. Min Act: -0.1700
Data Index: 2816376 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5401. Min Act: -0.1700
Data Index: 216457 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5401. Min Act: -0.1652
Data Index: 5965401 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5050. Min Act: -0.1682
Data Index: 8423459 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5050. Min Act: -0.1700
Data Index: 7576641 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8179. Min Range: -1.8179
Max Act: 1.5050. Min Act: -0.1661
Data Index: 1146370 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19