Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.5211. Min Act: -0.1700
Data Index: 1890710 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.3336. Min Act: -0.1700
Data Index: 2615588 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1461. Min Act: -0.1700
Data Index: 3055531 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1461. Min Act: -0.1700
Data Index: 4079354 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1461. Min Act: -0.1700
Data Index: 30085 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1461. Min Act: -0.1700
Data Index: 7049020 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1148. Min Act: -0.1700
Data Index: 3394440 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1148. Min Act: -0.1700
Data Index: 5435229 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.1148. Min Act: -0.1700
Data Index: 4353513 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.0836. Min Act: -0.1700
Data Index: 5135254 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.0523. Min Act: -0.1700
Data Index: 113323 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.0211. Min Act: -0.1700
Data Index: 2515727 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5211. Min Range: -5.5211
Max Act: 5.0211. Min Act: -0.1700
Data Index: 461047 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9898. Min Act: -0.1700
Data Index: 1645112 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9586. Min Act: -0.1700
Data Index: 8693702 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9586. Min Act: -0.1700
Data Index: 4369710 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.8961. Min Act: -0.1700
Data Index: 2979647 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 978197 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9586. Min Act: -0.1700
Data Index: 726525 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5211. Min Range: -5.5211
Max Act: 4.9273. Min Act: -0.1700
Data Index: 7180497 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19