Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5087 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4237. Min Range: -7.4237
Max Act: 7.4237. Min Act: -0.1700
Data Index: 2301361 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4237. Min Range: -7.4237
Max Act: 7.3925. Min Act: -0.1700
Data Index: 1697757 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4237. Min Range: -7.4237
Max Act: 7.2362. Min Act: -0.1700
Data Index: 7321119 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4237. Min Range: -7.4237
Max Act: 7.0800. Min Act: -0.1700
Data Index: 8589830 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4237. Min Range: -7.4237
Max Act: 7.0800. Min Act: -0.1700
Data Index: 8388618 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4237. Min Range: -7.4237
Max Act: 7.0175. Min Act: -0.1700
Data Index: 4348706 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.9862. Min Act: -0.1700
Data Index: 8253938 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.9550. Min Act: -0.1700
Data Index: 7738540 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.9237. Min Act: -0.1700
Data Index: 8719024 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.8925. Min Act: -0.1700
Data Index: 7439821 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.8925. Min Act: -0.1700
Data Index: 998059 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.7987. Min Act: -0.1700
Data Index: 1065394 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.8300. Min Act: -0.1700
Data Index: 8610212 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.8300. Min Act: -0.1700
Data Index: 5351447 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.7987. Min Act: -0.1700
Data Index: 96426 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.7987. Min Act: -0.1700
Data Index: 1679464 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.7675. Min Act: -0.1700
Data Index: 2165706 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.7675. Min Act: -0.1700
Data Index: 6016224 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.7362. Min Act: -0.1700
Data Index: 2501669 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4237. Min Range: -7.4237
Max Act: 6.7362. Min Act: -0.1700
Data Index: 5353374 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #19