Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1931. Min Range: -7.1931
Max Act: 7.1931. Min Act: -0.1700
Data Index: 1408292 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1931. Min Range: -7.1931
Max Act: 7.0681. Min Act: -0.1700
Data Index: 3417061 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.9431. Min Act: -0.1700
Data Index: 5425350 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.8181. Min Act: -0.1700
Data Index: 2301736 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.8181. Min Act: -0.1700
Data Index: 2340326 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.7869. Min Act: -0.1700
Data Index: 2815157 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.7556. Min Act: -0.1700
Data Index: 1374174 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.7244. Min Act: -0.1700
Data Index: 3505742 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.7244. Min Act: -0.1700
Data Index: 1142155 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.6931. Min Act: -0.1700
Data Index: 8697555 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.6619. Min Act: -0.1700
Data Index: 5409313 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.6619. Min Act: -0.1700
Data Index: 5699119 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.5994. Min Act: -0.1700
Data Index: 5079598 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.6306. Min Act: -0.1700
Data Index: 8669562 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.5994. Min Act: -0.1700
Data Index: 5113849 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.5994. Min Act: -0.1700
Data Index: 8060241 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.6306. Min Act: -0.1700
Data Index: 2377084 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.5994. Min Act: -0.1700
Data Index: 7464774 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.6306. Min Act: -0.1700
Data Index: 7288906 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1931. Min Range: -7.1931
Max Act: 6.5681. Min Act: -0.1700
Data Index: 4261595 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19