Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.8189. Min Act: -0.1700
Data Index: 4765772 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.6626. Min Act: -0.1700
Data Index: 8145713 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.5064. Min Act: -0.1700
Data Index: 4780163 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.4439. Min Act: -0.1700
Data Index: 7838309 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.4439. Min Act: -0.1700
Data Index: 2111945 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.3814. Min Act: -0.1700
Data Index: 958756 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.3501. Min Act: -0.1700
Data Index: 1768016 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.3189. Min Act: -0.1700
Data Index: 7475583 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.2564. Min Act: -0.1700
Data Index: 5194476 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.2251. Min Act: -0.1700
Data Index: 4330480 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1939. Min Act: -0.1700
Data Index: 6531162 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1939. Min Act: -0.1700
Data Index: 4213401 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1939. Min Act: -0.1700
Data Index: 7091714 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1626. Min Act: -0.1700
Data Index: 6004045 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1626. Min Act: -0.1700
Data Index: 8372999 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1939. Min Act: -0.1700
Data Index: 6830409 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1626. Min Act: -0.1700
Data Index: 4015621 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1314. Min Act: -0.1700
Data Index: 136966 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1314. Min Act: -0.1700
Data Index: 6136543 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8189. Min Range: -7.8189
Max Act: 7.1314. Min Act: -0.1700
Data Index: 2174690 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19