Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3801 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1395. Min Range: -3.1395
Max Act: 3.1395. Min Act: -0.1700
Data Index: 286436 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.8550. Min Act: -0.1700
Data Index: 4782649 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.8073. Min Act: -0.1700
Data Index: 3466040 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.8073. Min Act: -0.1700
Data Index: 5725958 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7595. Min Act: -0.1700
Data Index: 7132787 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7595. Min Act: -0.1700
Data Index: 6883449 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7754. Min Act: -0.1700
Data Index: 6217214 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7595. Min Act: -0.1700
Data Index: 7132786 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7275. Min Act: -0.1700
Data Index: 4783068 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7275. Min Act: -0.1700
Data Index: 7006183 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7115. Min Act: -0.1700
Data Index: 8114549 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.7115. Min Act: -0.1700
Data Index: 1241322 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6955. Min Act: -0.1700
Data Index: 157431 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6795. Min Act: -0.1700
Data Index: 7858447 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6955. Min Act: -0.1700
Data Index: 2318775 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6955. Min Act: -0.1700
Data Index: 1390140 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6955. Min Act: -0.1700
Data Index: 6809946 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6955. Min Act: -0.1700
Data Index: 5925624 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6795. Min Act: -0.1700
Data Index: 6852796 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1395. Min Range: -3.1395
Max Act: 2.6795. Min Act: -0.1700
Data Index: 5215116 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19