Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 1802290 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.6418. Min Act: -0.1700
Data Index: 6904232 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.6418. Min Act: -0.1700
Data Index: 2930189 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 1989080 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 5255536 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 5060745 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 2309563 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 1592059 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 8137220 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 7196146 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 3516170 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 8281001 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 6083190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 1025717 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 6440954 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 581471 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 4412956 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 554757 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 1890321 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4856. Min Act: -0.1700
Data Index: 3337169 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19