Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.5943. Min Act: -0.1700
Data Index: 495072 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.5630. Min Act: -0.1700
Data Index: 6720214 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.5630. Min Act: -0.1700
Data Index: 1746525 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.4693. Min Act: -0.1700
Data Index: 7215619 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.5005. Min Act: -0.1700
Data Index: 303328 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.4068. Min Act: -0.1700
Data Index: 495073 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.4068. Min Act: -0.1700
Data Index: 6611777 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.4693. Min Act: -0.1700
Data Index: 6288952 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3755. Min Act: -0.1700
Data Index: 3399014 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3755. Min Act: -0.1700
Data Index: 8097796 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3755. Min Act: -0.1700
Data Index: 4529697 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3755. Min Act: -0.1700
Data Index: 2579385 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3755. Min Act: -0.1700
Data Index: 5147235 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.2818. Min Act: -0.1700
Data Index: 5385670 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3130. Min Act: -0.1700
Data Index: 1159896 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3443. Min Act: -0.1700
Data Index: 2842396 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.2818. Min Act: -0.1700
Data Index: 8319996 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.3130. Min Act: -0.1700
Data Index: 132047 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.2818. Min Act: -0.1700
Data Index: 7235954 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5943. Min Range: -5.5943
Max Act: 5.2505. Min Act: -0.1700
Data Index: 5711528 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19