Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.5780. Min Act: -0.1700
Data Index: 4750325 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.3905. Min Act: -0.1700
Data Index: 6863006 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.3280. Min Act: -0.1700
Data Index: 3464331 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.2342. Min Act: -0.1700
Data Index: 7102801 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.2030. Min Act: -0.1700
Data Index: 3880990 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.2030. Min Act: -0.1700
Data Index: 8532835 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.2030. Min Act: -0.1700
Data Index: 4733056 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1717. Min Act: -0.1700
Data Index: 3812435 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1405. Min Act: -0.1700
Data Index: 5845023 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1717. Min Act: -0.1700
Data Index: 1845453 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 6364468 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 759399 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 8186002 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 3332789 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 398893 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 3678288 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 3574038 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.1092. Min Act: -0.1700
Data Index: 6222410 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.0780. Min Act: -0.1700
Data Index: 6254116 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5780. Min Range: -4.5780
Max Act: 4.0780. Min Act: -0.1700
Data Index: 1967271 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19