Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4297. Min Range: -4.4297
Max Act: 4.4297. Min Act: -0.1700
Data Index: 109857 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4297. Min Range: -4.4297
Max Act: 4.2422. Min Act: -0.1700
Data Index: 1473259 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4297. Min Range: -4.4297
Max Act: 4.1484. Min Act: -0.1700
Data Index: 4428216 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4297. Min Range: -4.4297
Max Act: 4.1171. Min Act: -0.1700
Data Index: 5950566 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4297. Min Range: -4.4297
Max Act: 4.0546. Min Act: -0.1700
Data Index: 5573195 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4297. Min Range: -4.4297
Max Act: 4.0546. Min Act: -0.1700
Data Index: 6265122 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9296. Min Act: -0.1700
Data Index: 7933643 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9921. Min Act: -0.1700
Data Index: 3124461 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9921. Min Act: -0.1700
Data Index: 7237838 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9921. Min Act: -0.1700
Data Index: 638852 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9296. Min Act: -0.1700
Data Index: 1608971 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9296. Min Act: -0.1700
Data Index: 1012245 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9608. Min Act: -0.1700
Data Index: 2342402 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9296. Min Act: -0.1700
Data Index: 5501560 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.8670. Min Act: -0.1700
Data Index: 4594071 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.8983. Min Act: -0.1700
Data Index: 6904342 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.9296. Min Act: -0.1700
Data Index: 4214827 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.8670. Min Act: -0.1700
Data Index: 3406444 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.8358. Min Act: -0.1700
Data Index: 6653527 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4297. Min Range: -4.4297
Max Act: 3.8983. Min Act: -0.1700
Data Index: 6199011 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19