Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1206. Min Range: -2.1206
Max Act: 2.1206. Min Act: -0.1700
Data Index: 2891171 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1206. Min Range: -2.1206
Max Act: 2.0367. Min Act: -0.1700
Data Index: 8251421 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1206. Min Range: -2.1206
Max Act: 2.0030. Min Act: -0.1700
Data Index: 8394268 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1206. Min Range: -2.1206
Max Act: 2.0030. Min Act: -0.1700
Data Index: 2285202 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9861. Min Act: -0.1700
Data Index: 7318794 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1206. Min Range: -2.1206
Max Act: 2.0030. Min Act: -0.1700
Data Index: 8454082 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1206. Min Range: -2.1206
Max Act: 2.0030. Min Act: -0.1700
Data Index: 2400631 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9776. Min Act: -0.1700
Data Index: 5531506 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9691. Min Act: -0.1700
Data Index: 5416484 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9607. Min Act: -0.1700
Data Index: 2891175 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9607. Min Act: -0.1700
Data Index: 6459570 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9691. Min Act: -0.1700
Data Index: 4025393 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9607. Min Act: -0.1700
Data Index: 7662549 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9607. Min Act: -0.1700
Data Index: 4572320 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9522. Min Act: -0.1700
Data Index: 3281080 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9607. Min Act: -0.1700
Data Index: 8251420 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9522. Min Act: -0.1700
Data Index: 7950738 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9352. Min Act: -0.1700
Data Index: 2337113 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9522. Min Act: -0.1700
Data Index: 5106630 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1206. Min Range: -2.1206
Max Act: 1.9352. Min Act: -0.1700
Data Index: 5316920 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19