Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1222 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.7520. Min Act: -0.1700
Data Index: 598653 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.7520. Min Act: -0.1700
Data Index: 8656365 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.7207. Min Act: -0.1700
Data Index: 6669410 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.6582. Min Act: -0.1700
Data Index: 5107414 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.6582. Min Act: -0.1700
Data Index: 3023163 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.6270. Min Act: -0.1700
Data Index: 8523939 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.6270. Min Act: -0.1700
Data Index: 1746246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.6270. Min Act: -0.1700
Data Index: 6402725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5957. Min Act: -0.1700
Data Index: 2729966 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5957. Min Act: -0.1700
Data Index: 3586733 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5957. Min Act: -0.1700
Data Index: 8023398 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5332. Min Act: -0.1700
Data Index: 3021939 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5332. Min Act: -0.1700
Data Index: 144490 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5332. Min Act: -0.1700
Data Index: 5157342 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5020. Min Act: -0.1700
Data Index: 5171669 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.4707. Min Act: -0.1700
Data Index: 2380342 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5332. Min Act: -0.1700
Data Index: 1468002 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.5332. Min Act: -0.1700
Data Index: 6755738 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.4707. Min Act: -0.1700
Data Index: 7332233 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7520. Min Range: -6.7520
Max Act: 6.4707. Min Act: -0.1700
Data Index: 1520371 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19