Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.4073. Min Act: -0.1700
Data Index: 375920 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3761. Min Act: -0.1700
Data Index: 762557 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3761. Min Act: -0.1700
Data Index: 6430222 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.4073. Min Act: -0.1699
Data Index: 6324977 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.4073. Min Act: -0.1700
Data Index: 3517519 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3761. Min Act: -0.1700
Data Index: 7481285 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3761. Min Act: -0.1700
Data Index: 7384858 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3448. Min Act: -0.1700
Data Index: 8236044 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3761. Min Act: -0.1694
Data Index: 7995990 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3448. Min Act: -0.1700
Data Index: 8461 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3448. Min Act: -0.1699
Data Index: 2707269 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3448. Min Act: -0.1700
Data Index: 7317576 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3448. Min Act: -0.1700
Data Index: 2228185 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.3136. Min Act: -0.1700
Data Index: 1551383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.2823. Min Act: -0.1700
Data Index: 7370638 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.2823. Min Act: -0.1700
Data Index: 6206856 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.2823. Min Act: -0.1700
Data Index: 4399543 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.2823. Min Act: -0.1700
Data Index: 1857175 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.2823. Min Act: -0.1700
Data Index: 1855418 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4073. Min Range: -5.4073
Max Act: 5.2823. Min Act: -0.1700
Data Index: 1329014 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19