Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4488 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4995. Min Act: -0.1700
Data Index: 1777689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4995. Min Act: -0.1700
Data Index: 2993880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4995. Min Act: -0.1700
Data Index: 8173491 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 6306750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4681. Min Act: -0.1700
Data Index: 984501 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4681. Min Act: -0.1700
Data Index: 6009655 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4681. Min Act: -0.1700
Data Index: 4037379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 498674 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4054. Min Act: -0.1700
Data Index: 3205206 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 4016562 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4054. Min Act: -0.1700
Data Index: 3169943 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 4930219 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 229272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 716938 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 3094290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 281704 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 2450638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 345685 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4054. Min Act: -0.1700
Data Index: 3014585 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4995. Min Range: -3.4995
Max Act: 3.4368. Min Act: -0.1700
Data Index: 6114056 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19