Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.5138. Min Act: -0.1700
Data Index: 6118479 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.2950. Min Act: -0.1700
Data Index: 6976853 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.2013. Min Act: -0.1700
Data Index: 4735984 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.1700. Min Act: -0.1700
Data Index: 1327358 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.1388. Min Act: -0.1700
Data Index: 7563425 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.1075. Min Act: -0.1700
Data Index: 3581209 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.1388. Min Act: -0.1700
Data Index: 6214586 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.1075. Min Act: -0.1700
Data Index: 2511957 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.1075. Min Act: -0.1700
Data Index: 4603525 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0450. Min Act: -0.1700
Data Index: 5627016 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0450. Min Act: -0.1700
Data Index: 800967 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6983870 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0763. Min Act: -0.1700
Data Index: 4953805 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0138. Min Act: -0.1700
Data Index: 2777335 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0138. Min Act: -0.1700
Data Index: 3124806 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0138. Min Act: -0.1700
Data Index: 3139742 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0138. Min Act: -0.1700
Data Index: 4951335 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0450. Min Act: -0.1700
Data Index: 7235592 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0138. Min Act: -0.1700
Data Index: 5311695 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5138. Min Range: -5.5138
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6118478 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19