Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1402 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.6451. Min Act: -0.1700
Data Index: 4496918 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.6608. Min Act: -0.1700
Data Index: 3122217 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.6138. Min Act: -0.1700
Data Index: 8796024 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.5825. Min Act: -0.1700
Data Index: 8633150 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.5669. Min Act: -0.1700
Data Index: 5873315 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.5043. Min Act: -0.1700
Data Index: 5758831 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4102. Min Act: -0.1700
Data Index: 4864210 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4102. Min Act: -0.1700
Data Index: 4709083 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4259. Min Act: -0.1700
Data Index: 2863634 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3946. Min Act: -0.1700
Data Index: 6346757 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4102. Min Act: -0.1700
Data Index: 3766566 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3946. Min Act: -0.1700
Data Index: 410121 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.4102. Min Act: -0.1700
Data Index: 564847 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3946. Min Act: -0.1700
Data Index: 2260548 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3789. Min Act: -0.1700
Data Index: 7698837 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3789. Min Act: -0.1700
Data Index: 1952086 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3789. Min Act: -0.1700
Data Index: 4037438 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3632. Min Act: -0.1700
Data Index: 6670766 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3318. Min Act: -0.1700
Data Index: 8366952 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6608. Min Range: -3.6608
Max Act: 3.3632. Min Act: -0.1700
Data Index: 6944699 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19