Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5120. Min Range: -7.5120
Max Act: 7.5120. Min Act: -0.1700
Data Index: 4692141 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5120. Min Range: -7.5120
Max Act: 7.2932. Min Act: -0.1700
Data Index: 802667 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5120. Min Range: -7.5120
Max Act: 7.1995. Min Act: -0.1700
Data Index: 3427048 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5120. Min Range: -7.5120
Max Act: 7.1682. Min Act: -0.1700
Data Index: 5472495 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5120. Min Range: -7.5120
Max Act: 7.1370. Min Act: -0.1700
Data Index: 7151316 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5120. Min Range: -7.5120
Max Act: 7.1370. Min Act: -0.1700
Data Index: 3958896 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5120. Min Range: -7.5120
Max Act: 7.0745. Min Act: -0.1700
Data Index: 6508106 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.9807. Min Act: -0.1700
Data Index: 8449032 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.9807. Min Act: -0.1700
Data Index: 7096444 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.8245. Min Act: -0.1700
Data Index: 8109473 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.7932. Min Act: -0.1700
Data Index: 8119045 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.8245. Min Act: -0.1700
Data Index: 6010750 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.8245. Min Act: -0.1700
Data Index: 8745035 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.8245. Min Act: -0.1700
Data Index: 5116589 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.7932. Min Act: -0.1700
Data Index: 5126962 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8807881 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.7620. Min Act: -0.1700
Data Index: 5590518 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.7307. Min Act: -0.1700
Data Index: 7666475 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.7307. Min Act: -0.1700
Data Index: 1971838 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5120. Min Range: -7.5120
Max Act: 6.6682. Min Act: -0.1700
Data Index: 4441053 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19