Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.7963. Min Act: -0.1700
Data Index: 2696426 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.7338. Min Act: -0.1700
Data Index: 4445118 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.7026. Min Act: -0.1700
Data Index: 6467356 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.7026. Min Act: -0.1700
Data Index: 1146995 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.6088. Min Act: -0.1700
Data Index: 8288877 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.6713. Min Act: -0.1700
Data Index: 4357925 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.6401. Min Act: -0.1700
Data Index: 5550064 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.6401. Min Act: -0.1700
Data Index: 5702472 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.6088. Min Act: -0.1700
Data Index: 6592902 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.6088. Min Act: -0.1700
Data Index: 6656927 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.6088. Min Act: -0.1700
Data Index: 1661559 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.5463. Min Act: -0.1700
Data Index: 6436006 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.5151. Min Act: -0.1700
Data Index: 96306 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.5463. Min Act: -0.1700
Data Index: 2176848 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.5151. Min Act: -0.1700
Data Index: 353881 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.4838. Min Act: -0.1700
Data Index: 7056009 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.4526. Min Act: -0.1700
Data Index: 8372265 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.4213. Min Act: -0.1700
Data Index: 7448089 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.3588. Min Act: -0.1700
Data Index: 3238017 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7963. Min Range: -7.7963
Max Act: 7.3588. Min Act: -0.1700
Data Index: 2900968 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19