Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4421 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3788. Min Act: -0.1700
Data Index: 8000314 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3163. Min Act: -0.1700
Data Index: 7924998 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3163. Min Act: -0.1700
Data Index: 3842219 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3163. Min Act: -0.1700
Data Index: 8795919 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3163. Min Act: -0.1700
Data Index: 518988 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3163. Min Act: -0.1700
Data Index: 8259324 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3163. Min Act: -0.1700
Data Index: 8115254 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3163. Min Act: -0.1700
Data Index: 6932131 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.3476. Min Act: -0.1700
Data Index: 36658 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2851. Min Act: -0.1700
Data Index: 7384144 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2851. Min Act: -0.1700
Data Index: 4319800 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2538. Min Act: -0.1700
Data Index: 7877145 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2538. Min Act: -0.1700
Data Index: 8786859 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2538. Min Act: -0.1700
Data Index: 771663 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2538. Min Act: -0.1700
Data Index: 2183607 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2226. Min Act: -0.1700
Data Index: 1632727 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2226. Min Act: -0.1700
Data Index: 4557281 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2226. Min Act: -0.1700
Data Index: 2970293 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2226. Min Act: -0.1700
Data Index: 2319942 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3788. Min Range: -4.3788
Max Act: 4.2226. Min Act: -0.1700
Data Index: 8492700 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19