Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4440 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.9214. Min Act: -0.1700
Data Index: 4308959 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.9214. Min Act: -0.1700
Data Index: 8113850 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.8277. Min Act: -0.1700
Data Index: 5756960 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.8277. Min Act: -0.1700
Data Index: 95190 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.8277. Min Act: -0.1700
Data Index: 247102 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7964. Min Act: -0.1700
Data Index: 4039990 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7964. Min Act: -0.1700
Data Index: 4139384 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7652. Min Act: -0.1700
Data Index: 5751832 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7652. Min Act: -0.1700
Data Index: 2620848 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7652. Min Act: -0.1700
Data Index: 2939015 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7027. Min Act: -0.1700
Data Index: 2303145 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7339. Min Act: -0.1700
Data Index: 412368 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7339. Min Act: -0.1700
Data Index: 2791821 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7339. Min Act: -0.1700
Data Index: 2041985 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7339. Min Act: -0.1700
Data Index: 4001790 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7339. Min Act: -0.1700
Data Index: 3472221 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7339. Min Act: -0.1700
Data Index: 7769606 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7027. Min Act: -0.1700
Data Index: 2098406 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7027. Min Act: -0.1700
Data Index: 2776899 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9214. Min Range: -5.9214
Max Act: 5.7027. Min Act: -0.1700
Data Index: 1254706 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19