Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2118 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.4728. Min Act: -0.1700
Data Index: 3035461 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.3790. Min Act: -0.1700
Data Index: 6708659 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.3478. Min Act: -0.1700
Data Index: 8696467 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.3478. Min Act: -0.1700
Data Index: 7454492 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.2853. Min Act: -0.1700
Data Index: 3775936 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.2853. Min Act: -0.1700
Data Index: 707276 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.2540. Min Act: -0.1700
Data Index: 1503278 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.2228. Min Act: -0.1700
Data Index: 3612952 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.2228. Min Act: -0.1700
Data Index: 4586124 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.1603. Min Act: -0.1700
Data Index: 2547185 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 6121110 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 3746503 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 7810027 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 8188802 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 2251875 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.1290. Min Act: -0.1700
Data Index: 7666005 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.0353. Min Act: -0.1700
Data Index: 1295404 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.0353. Min Act: -0.1700
Data Index: 2303007 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.0353. Min Act: -0.1700
Data Index: 7888853 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4728. Min Range: -7.4728
Max Act: 7.0353. Min Act: -0.1700
Data Index: 1954543 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19