Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1560 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4940. Min Act: -0.1634
Data Index: 6234651 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4940. Min Act: -0.1699
Data Index: 2086956 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4627. Min Act: -0.1691
Data Index: 1682210 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4627. Min Act: -0.1690
Data Index: 3416143 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4314. Min Act: -0.1651
Data Index: 296763 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4314. Min Act: -0.1697
Data Index: 2012318 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4314. Min Act: -0.1696
Data Index: 2339543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4314. Min Act: -0.1596
Data Index: 2889337 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4314. Min Act: -0.1696
Data Index: 6497226 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4314. Min Act: -0.1692
Data Index: 8681611 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4000. Min Act: -0.1698
Data Index: 7862709 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4000. Min Act: -0.1694
Data Index: 2444320 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4000. Min Act: -0.1670
Data Index: 556311 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.3686. Min Act: -0.1700
Data Index: 1777177 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.3686. Min Act: -0.1698
Data Index: 1167112 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4000. Min Act: -0.1618
Data Index: 934268 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.3686. Min Act: -0.1567
Data Index: 3810536 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4000. Min Act: -0.1645
Data Index: 4001320 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.4000. Min Act: -0.1698
Data Index: 1961955 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4940. Min Range: -3.4940
Max Act: 3.3686. Min Act: -0.1427
Data Index: 4934408 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19