Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0449. Min Range: -6.0449
Max Act: 6.0449. Min Act: -0.1700
Data Index: 5610282 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0449. Min Range: -6.0449
Max Act: 6.0137. Min Act: -0.1700
Data Index: 4925842 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.9512. Min Act: -0.1700
Data Index: 7320299 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.9824. Min Act: -0.1700
Data Index: 7769885 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.9512. Min Act: -0.1700
Data Index: 5318931 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.9199. Min Act: -0.1700
Data Index: 1968554 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.8574. Min Act: -0.1700
Data Index: 6393280 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.8574. Min Act: -0.1700
Data Index: 2196157 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.8574. Min Act: -0.1700
Data Index: 6087115 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7949. Min Act: -0.1700
Data Index: 3009490 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7949. Min Act: -0.1700
Data Index: 2690324 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7949. Min Act: -0.1700
Data Index: 8572375 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7949. Min Act: -0.1700
Data Index: 184337 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7275667 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7637. Min Act: -0.1700
Data Index: 94663 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7637. Min Act: -0.1700
Data Index: 7440032 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 6631448 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7637. Min Act: -0.1700
Data Index: 7796659 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 7194062 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 2308764 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19