Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3700 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.5529. Min Act: -0.1700
Data Index: 7722981 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.2092. Min Act: -0.1700
Data Index: 1245425 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.1467. Min Act: -0.1700
Data Index: 6344772 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0842. Min Act: -0.1700
Data Index: 3773401 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0842. Min Act: -0.1700
Data Index: 463759 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0529. Min Act: -0.1700
Data Index: 1748143 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0529. Min Act: -0.1700
Data Index: 8367073 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0529. Min Act: -0.1700
Data Index: 7102017 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0529. Min Act: -0.1700
Data Index: 1070911 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0529. Min Act: -0.1700
Data Index: 4592521 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5529. Min Range: -6.5529
Max Act: 6.0217. Min Act: -0.1700
Data Index: 5920491 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.9904. Min Act: -0.1700
Data Index: 3220439 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.9279. Min Act: -0.1700
Data Index: 7801886 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.9279. Min Act: -0.1700
Data Index: 8788600 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.9279. Min Act: -0.1700
Data Index: 8109932 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.8967. Min Act: -0.1700
Data Index: 1491956 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.8967. Min Act: -0.1700
Data Index: 8404925 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.8967. Min Act: -0.1700
Data Index: 6372815 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.8967. Min Act: -0.1700
Data Index: 3732964 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5529. Min Range: -6.5529
Max Act: 5.8654. Min Act: -0.1700
Data Index: 1003071 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19