Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5253 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.5469. Min Act: -0.1700
Data Index: 1109263 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.3432. Min Act: -0.1700
Data Index: 2576464 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.2490. Min Act: -0.1700
Data Index: 5571118 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.2647. Min Act: -0.1700
Data Index: 6789125 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.2647. Min Act: -0.1700
Data Index: 2274784 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.2333. Min Act: -0.1700
Data Index: 6789122 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.1861. Min Act: -0.1700
Data Index: 7210541 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.1546. Min Act: -0.1700
Data Index: 6598015 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.1074. Min Act: -0.1700
Data Index: 587507 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0916. Min Act: -0.1700
Data Index: 8100638 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0759. Min Act: -0.1700
Data Index: 8568113 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0916. Min Act: -0.1700
Data Index: 3809914 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0916. Min Act: -0.1700
Data Index: 2812579 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0601. Min Act: -0.1700
Data Index: 1445456 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0601. Min Act: -0.1700
Data Index: 7640253 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0601. Min Act: -0.1700
Data Index: 4439092 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0443. Min Act: -0.1700
Data Index: 8796053 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0443. Min Act: -0.1700
Data Index: 1450131 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0443. Min Act: -0.1700
Data Index: 1764482 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5469. Min Range: -3.5469
Max Act: 3.0285. Min Act: -0.1700
Data Index: 6937522 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19