Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4469 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.8233. Min Act: -0.1700
Data Index: 5558364 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.6358. Min Act: -0.1700
Data Index: 2981356 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.6046. Min Act: -0.1700
Data Index: 5355488 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.5733. Min Act: -0.1700
Data Index: 4503226 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.5733. Min Act: -0.1700
Data Index: 7887832 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.5421. Min Act: -0.1700
Data Index: 2897026 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.4483. Min Act: -0.1700
Data Index: 7275192 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.4171. Min Act: -0.1700
Data Index: 3196885 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.3858. Min Act: -0.1700
Data Index: 2743592 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.3546. Min Act: -0.1700
Data Index: 391367 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.3233. Min Act: -0.1700
Data Index: 589748 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.3233. Min Act: -0.1700
Data Index: 3428307 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.2296. Min Act: -0.1700
Data Index: 2999756 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.2296. Min Act: -0.1700
Data Index: 2076973 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.1983. Min Act: -0.1700
Data Index: 2685308 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.1671. Min Act: -0.1700
Data Index: 6401387 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.1671. Min Act: -0.1700
Data Index: 5181245 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.1671. Min Act: -0.1700
Data Index: 7214537 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.1358. Min Act: -0.1700
Data Index: 1550153 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8233. Min Range: -7.8233
Max Act: 7.1671. Min Act: -0.1700
Data Index: 1759263 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19