Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3062 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.9999. Min Act: -0.1700
Data Index: 5957915 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.9826. Min Act: -0.1700
Data Index: 1023603 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.9653. Min Act: -0.1700
Data Index: 7400697 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.9308. Min Act: -0.1700
Data Index: 3603491 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.9137. Min Act: -0.1700
Data Index: 1091966 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.9137. Min Act: -0.1700
Data Index: 524772 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.9137. Min Act: -0.1700
Data Index: 1418137 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8965. Min Act: -0.1697
Data Index: 5466172 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8965. Min Act: -0.1700
Data Index: 2211204 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8965. Min Act: -0.1700
Data Index: 7693418 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8965. Min Act: -0.1700
Data Index: 4847216 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 2069480 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 2106368 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 2397176 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 2501457 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8624. Min Act: -0.1700
Data Index: 3781315 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 715461 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 2792353 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 1027791 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9999. Min Range: -0.9999
Max Act: 0.8795. Min Act: -0.1700
Data Index: 6111826 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19