Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.7723. Min Act: -0.1700
Data Index: 6659877 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 4867181 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 208462 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6160. Min Act: -0.1700
Data Index: 6723010 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.5535. Min Act: -0.1700
Data Index: 4047350 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.5223. Min Act: -0.1700
Data Index: 1163369 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.4598. Min Act: -0.1700
Data Index: 5942003 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.4285. Min Act: -0.1700
Data Index: 1887566 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3973. Min Act: -0.1700
Data Index: 29758 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3660. Min Act: -0.1700
Data Index: 1827016 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3660. Min Act: -0.1700
Data Index: 295338 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3035. Min Act: -0.1700
Data Index: 7986842 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3035. Min Act: -0.1700
Data Index: 8193130 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3348. Min Act: -0.1700
Data Index: 2613457 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3035. Min Act: -0.1700
Data Index: 3007025 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3348. Min Act: -0.1700
Data Index: 7842654 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3348. Min Act: -0.1700
Data Index: 2078189 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3035. Min Act: -0.1700
Data Index: 6805561 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3348. Min Act: -0.1700
Data Index: 6313229 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.3348. Min Act: -0.1700
Data Index: 1468986 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19