Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2017 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.4680. Min Act: -0.1700
Data Index: 7183970 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.4680. Min Act: -0.1700
Data Index: 7811731 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.3742. Min Act: -0.1700
Data Index: 604874 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.3742. Min Act: -0.1700
Data Index: 252160 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.3430. Min Act: -0.1700
Data Index: 4846781 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.3117. Min Act: -0.1700
Data Index: 3949306 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.3117. Min Act: -0.1700
Data Index: 3369359 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.2492. Min Act: -0.1700
Data Index: 2359051 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.2180. Min Act: -0.1700
Data Index: 4846783 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1867. Min Act: -0.1700
Data Index: 5679348 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1555. Min Act: -0.1700
Data Index: 623394 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1555. Min Act: -0.1700
Data Index: 4947944 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1555. Min Act: -0.1700
Data Index: 8479799 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1242. Min Act: -0.1700
Data Index: 8393221 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0930. Min Act: -0.1700
Data Index: 2522817 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1242. Min Act: -0.1700
Data Index: 6059560 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1242. Min Act: -0.1700
Data Index: 4022436 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0930. Min Act: -0.1700
Data Index: 5373560 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0930. Min Act: -0.1700
Data Index: 2781045 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0617. Min Act: -0.1700
Data Index: 3702252 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19