Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2509 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.4402. Min Act: -0.1700
Data Index: 6832075 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.3932. Min Act: -0.1700
Data Index: 4005038 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.3618. Min Act: -0.1700
Data Index: 200223 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.3462. Min Act: -0.1700
Data Index: 8399637 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.3462. Min Act: -0.1700
Data Index: 8217574 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2991. Min Act: -0.1700
Data Index: 8368972 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2834. Min Act: -0.1700
Data Index: 2454723 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2834. Min Act: -0.1700
Data Index: 8399634 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2834. Min Act: -0.1700
Data Index: 4513186 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2834. Min Act: -0.1700
Data Index: 2767897 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2834. Min Act: -0.1700
Data Index: 5437701 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2834. Min Act: -0.1700
Data Index: 927168 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2362. Min Act: -0.1700
Data Index: 5437827 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2520. Min Act: -0.1700
Data Index: 7841505 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2362. Min Act: -0.1700
Data Index: 5088471 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2362. Min Act: -0.1700
Data Index: 5013526 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2205. Min Act: -0.1700
Data Index: 7888848 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2205. Min Act: -0.1700
Data Index: 5712155 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2205. Min Act: -0.1700
Data Index: 2708782 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4402. Min Range: -3.4402
Max Act: 3.2205. Min Act: -0.1700
Data Index: 7849510 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19