Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6279 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2907. Min Range: -9.2907
Max Act: 9.2907. Min Act: -0.1700
Data Index: 7488776 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.9157. Min Act: -0.1700
Data Index: 6629052 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.7282. Min Act: -0.1700
Data Index: 5512819 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.7282. Min Act: -0.1700
Data Index: 1339597 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.7282. Min Act: -0.1700
Data Index: 1143933 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.6657. Min Act: -0.1700
Data Index: 8480303 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.6032. Min Act: -0.1700
Data Index: 8283245 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.6032. Min Act: -0.1700
Data Index: 5192127 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.6032. Min Act: -0.1700
Data Index: 681315 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.6032. Min Act: -0.1700
Data Index: 5082378 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4782. Min Act: -0.1700
Data Index: 4647774 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4782. Min Act: -0.1700
Data Index: 7683110 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4782. Min Act: -0.1700
Data Index: 6900144 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4782. Min Act: -0.1700
Data Index: 206741 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4782. Min Act: -0.1700
Data Index: 4652391 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4157. Min Act: -0.1700
Data Index: 3790550 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4157. Min Act: -0.1700
Data Index: 1375859 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4157. Min Act: -0.1700
Data Index: 5375212 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4157. Min Act: -0.1700
Data Index: 6927122 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2907. Min Range: -9.2907
Max Act: 8.4157. Min Act: -0.1700
Data Index: 6361937 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19