Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.7858. Min Act: -0.1700
Data Index: 1172828 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6920. Min Act: -0.1700
Data Index: 8054521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6920. Min Act: -0.1700
Data Index: 5900889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6920. Min Act: -0.1700
Data Index: 2481463 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6920. Min Act: -0.1700
Data Index: 2701445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 8326961 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6607. Min Act: -0.1700
Data Index: 1248 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6607. Min Act: -0.1700
Data Index: 6554512 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6607. Min Act: -0.1700
Data Index: 1243640 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 4182554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 7904240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 7867280 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 7740179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.5981. Min Act: -0.1700
Data Index: 7703228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 7198208 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 7118838 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 5917941 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 5583018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.6294. Min Act: -0.1700
Data Index: 1979118 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7858. Min Range: -3.7858
Max Act: 3.5981. Min Act: -0.1700
Data Index: 5247528 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19