Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.4987. Min Act: -0.1700
Data Index: 113479 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.3425. Min Act: -0.1700
Data Index: 5514800 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.2487. Min Act: -0.1700
Data Index: 3609452 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.2487. Min Act: -0.1700
Data Index: 6855177 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.2487. Min Act: -0.1700
Data Index: 4206208 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.2175. Min Act: -0.1700
Data Index: 3544518 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.1862. Min Act: -0.1700
Data Index: 1791702 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.0612. Min Act: -0.1700
Data Index: 6758619 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.0612. Min Act: -0.1700
Data Index: 3609454 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.0300. Min Act: -0.1700
Data Index: 2495682 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.0612. Min Act: -0.1700
Data Index: 4302826 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.0612. Min Act: -0.1700
Data Index: 8553060 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4987. Min Range: -5.4987
Max Act: 5.0612. Min Act: -0.1700
Data Index: 7068540 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4987. Min Range: -5.4987
Max Act: 4.9362. Min Act: -0.1700
Data Index: 2481304 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4987. Min Range: -5.4987
Max Act: 4.9675. Min Act: -0.1700
Data Index: 501502 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4987. Min Range: -5.4987
Max Act: 4.9362. Min Act: -0.1700
Data Index: 7413627 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4987. Min Range: -5.4987
Max Act: 4.9362. Min Act: -0.1700
Data Index: 2175249 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4987. Min Range: -5.4987
Max Act: 4.9050. Min Act: -0.1700
Data Index: 6878783 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4987. Min Range: -5.4987
Max Act: 4.9050. Min Act: -0.1700
Data Index: 4431683 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4987. Min Range: -5.4987
Max Act: 4.9050. Min Act: -0.1700
Data Index: 7063612 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19