Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.7136. Min Act: -0.1699
Data Index: 6616198 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.6511. Min Act: -0.1700
Data Index: 807133 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.6199. Min Act: -0.1700
Data Index: 1858211 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.5261. Min Act: -0.1686
Data Index: 1866374 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.4636. Min Act: -0.1700
Data Index: 7993997 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.4636. Min Act: -0.1700
Data Index: 7993998 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.4324. Min Act: -0.1700
Data Index: 8268605 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3699. Min Act: -0.1637
Data Index: 8620944 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3699. Min Act: -0.1700
Data Index: 438363 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3386. Min Act: -0.1700
Data Index: 4804583 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3074. Min Act: -0.1700
Data Index: 5521137 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3386. Min Act: -0.1700
Data Index: 7441083 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3386. Min Act: -0.1700
Data Index: 161704 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3074. Min Act: -0.1700
Data Index: 4496117 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3074. Min Act: -0.1700
Data Index: 7441086 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3074. Min Act: -0.1700
Data Index: 2639507 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.3074. Min Act: -0.1700
Data Index: 958264 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.2761. Min Act: -0.1700
Data Index: 5899332 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.2761. Min Act: -0.1700
Data Index: 7406327 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7136. Min Range: -5.7136
Max Act: 5.2761. Min Act: -0.1700
Data Index: 7994698 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19