Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2105. Min Range: -9.2105
Max Act: 9.2105. Min Act: -0.1700
Data Index: 1156493 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2105. Min Range: -9.2105
Max Act: 9.1480. Min Act: -0.1700
Data Index: 1479241 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2105. Min Range: -9.2105
Max Act: 9.1480. Min Act: -0.1700
Data Index: 4415650 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2105. Min Range: -9.2105
Max Act: 9.0855. Min Act: -0.1700
Data Index: 7587590 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2105. Min Range: -9.2105
Max Act: 9.0230. Min Act: -0.1700
Data Index: 6591072 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2105. Min Range: -9.2105
Max Act: 9.0230. Min Act: -0.1700
Data Index: 5307577 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2105. Min Range: -9.2105
Max Act: 9.0230. Min Act: -0.1700
Data Index: 2819449 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.9605. Min Act: -0.1700
Data Index: 2551895 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.9605. Min Act: -0.1700
Data Index: 7722670 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8980. Min Act: -0.1700
Data Index: 1707843 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8980. Min Act: -0.1700
Data Index: 4229615 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8980. Min Act: -0.1700
Data Index: 2355014 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8980. Min Act: -0.1700
Data Index: 169238 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8980. Min Act: -0.1700
Data Index: 1142169 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8980. Min Act: -0.1700
Data Index: 3219327 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8980. Min Act: -0.1700
Data Index: 4110148 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.8355. Min Act: -0.1700
Data Index: 6978924 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.7730. Min Act: -0.1700
Data Index: 766224 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.7105. Min Act: -0.1700
Data Index: 48123 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2105. Min Range: -9.2105
Max Act: 8.7105. Min Act: -0.1700
Data Index: 394573 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19