Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.7213. Min Act: -0.1700
Data Index: 8595566 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.7213. Min Act: -0.1700
Data Index: 1980180 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.5963. Min Act: -0.1700
Data Index: 7891668 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.6275. Min Act: -0.1700
Data Index: 6106149 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.4713. Min Act: -0.1700
Data Index: 2496958 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.4400. Min Act: -0.1700
Data Index: 7879941 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.4088. Min Act: -0.1700
Data Index: 6260520 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.4088. Min Act: -0.1700
Data Index: 2433484 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.4088. Min Act: -0.1700
Data Index: 1562881 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.3775. Min Act: -0.1700
Data Index: 8678374 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.3775. Min Act: -0.1700
Data Index: 5916635 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.2837. Min Act: -0.1700
Data Index: 7808877 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.2837. Min Act: -0.1700
Data Index: 6080108 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.2837. Min Act: -0.1700
Data Index: 6714949 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.2525. Min Act: -0.1700
Data Index: 4611306 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.2212. Min Act: -0.1700
Data Index: 1903342 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.2212. Min Act: -0.1700
Data Index: 7331027 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.1900. Min Act: -0.1700
Data Index: 2585540 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.1587. Min Act: -0.1700
Data Index: 6577103 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7213. Min Range: -4.7213
Max Act: 4.1587. Min Act: -0.1700
Data Index: 7445873 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19