Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.2652. Min Act: -0.1700
Data Index: 7209806 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1714. Min Act: -0.1700
Data Index: 2765198 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1714. Min Act: -0.1700
Data Index: 3158620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1089. Min Act: -0.1700
Data Index: 4100152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1402. Min Act: -0.1700
Data Index: 7677643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1402. Min Act: -0.1700
Data Index: 8241559 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1089. Min Act: -0.1700
Data Index: 1668579 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1089. Min Act: -0.1700
Data Index: 68295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0777. Min Act: -0.1700
Data Index: 7327823 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1089. Min Act: -0.1700
Data Index: 5284554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1089. Min Act: -0.1700
Data Index: 3835782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.1089. Min Act: -0.1700
Data Index: 6035619 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0777. Min Act: -0.1700
Data Index: 3975149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0777. Min Act: -0.1700
Data Index: 6221963 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0777. Min Act: -0.1700
Data Index: 5555972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0777. Min Act: -0.1700
Data Index: 1854179 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0464. Min Act: -0.1700
Data Index: 2622368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0152. Min Act: -0.1700
Data Index: 3900402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0464. Min Act: -0.1700
Data Index: 6835760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2652. Min Range: -5.2652
Max Act: 5.0464. Min Act: -0.1700
Data Index: 522063 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19