Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2653 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.4104. Min Act: -0.1700
Data Index: 5400849 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3791. Min Act: -0.1700
Data Index: 4422944 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3791. Min Act: -0.1700
Data Index: 4856727 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3791. Min Act: -0.1700
Data Index: 5375067 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3477. Min Act: -0.1700
Data Index: 169737 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3477. Min Act: -0.1700
Data Index: 7151835 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3477. Min Act: -0.1700
Data Index: 4702726 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3477. Min Act: -0.1700
Data Index: 2932927 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3477. Min Act: -0.1700
Data Index: 6337761 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 7558539 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 2520859 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.2849. Min Act: -0.1700
Data Index: 7148275 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 4259239 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 5834579 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 1831082 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 3106016 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 1363496 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 4634977 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 1184604 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4104. Min Range: -3.4104
Max Act: 3.3163. Min Act: -0.1700
Data Index: 2574151 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19