Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2101 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.7198. Min Act: -0.1700
Data Index: 8178064 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.6261. Min Act: -0.1700
Data Index: 4425692 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4698. Min Act: -0.1700
Data Index: 2310055 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4698. Min Act: -0.1700
Data Index: 2308515 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 7474212 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4073. Min Act: -0.1700
Data Index: 2966252 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3761. Min Act: -0.1700
Data Index: 224490 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 4062893 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 4475780 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 8021027 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 2466206 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 3258042 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 1506837 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 1114337 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 734118 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.2823. Min Act: -0.1700
Data Index: 5581785 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3136. Min Act: -0.1700
Data Index: 3671285 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3136. Min Act: -0.1700
Data Index: 5460893 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.2823. Min Act: -0.1700
Data Index: 6415365 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.2823. Min Act: -0.1700
Data Index: 3411776 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19