Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4031 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 8109091 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0650. Min Act: -0.1700
Data Index: 8460464 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0025. Min Act: -0.1700
Data Index: 1834367 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0025. Min Act: -0.1700
Data Index: 1880187 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0025. Min Act: -0.1700
Data Index: 7898914 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0650. Min Range: -5.0650
Max Act: 5.0338. Min Act: -0.1700
Data Index: 3038502 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9713. Min Act: -0.1700
Data Index: 1417325 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 5955151 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9400. Min Act: -0.1700
Data Index: 5179464 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8775. Min Act: -0.1700
Data Index: 7311522 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9088. Min Act: -0.1700
Data Index: 3438339 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8775. Min Act: -0.1700
Data Index: 645022 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9088. Min Act: -0.1700
Data Index: 6834742 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9088. Min Act: -0.1700
Data Index: 2498630 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.9088. Min Act: -0.1700
Data Index: 8562387 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8463. Min Act: -0.1700
Data Index: 3867685 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8463. Min Act: -0.1700
Data Index: 202255 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8463. Min Act: -0.1700
Data Index: 3252800 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8463. Min Act: -0.1700
Data Index: 1817074 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0650. Min Range: -5.0650
Max Act: 4.8150. Min Act: -0.1700
Data Index: 4737859 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19