Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.6386. Min Act: -0.1700
Data Index: 6166069 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.6386. Min Act: -0.1700
Data Index: 3559985 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.6074. Min Act: -0.1700
Data Index: 3055259 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.6074. Min Act: -0.1700
Data Index: 6107009 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5761. Min Act: -0.1700
Data Index: 2545450 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5761. Min Act: -0.1700
Data Index: 4409137 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5761. Min Act: -0.1700
Data Index: 7242170 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5761. Min Act: -0.1700
Data Index: 5713986 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5761. Min Act: -0.1700
Data Index: 5764039 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 2834258 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 1879646 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 6894183 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 112029 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 6812677 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 3299029 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 1617515 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5136. Min Act: -0.1700
Data Index: 5003424 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5449. Min Act: -0.1700
Data Index: 1113417 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5136. Min Act: -0.1700
Data Index: 4008532 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6386. Min Range: -5.6386
Max Act: 5.5136. Min Act: -0.1700
Data Index: 1605044 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19