Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2464 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.4656. Min Act: -0.1700
Data Index: 1736648 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.4656. Min Act: -0.1700
Data Index: 8681549 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.4031. Min Act: -0.1700
Data Index: 7542742 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.4656. Min Act: -0.1700
Data Index: 1095905 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.3093. Min Act: -0.1700
Data Index: 1039710 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.3093. Min Act: -0.1700
Data Index: 5995148 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2781. Min Act: -0.1700
Data Index: 4498861 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.3093. Min Act: -0.1700
Data Index: 5017802 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2781. Min Act: -0.1700
Data Index: 4733036 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.3093. Min Act: -0.1700
Data Index: 6174211 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2468. Min Act: -0.1700
Data Index: 1371716 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2468. Min Act: -0.1700
Data Index: 8681552 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2781. Min Act: -0.1700
Data Index: 8681533 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7123523 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2468. Min Act: -0.1700
Data Index: 114305 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2468. Min Act: -0.1700
Data Index: 2108922 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2781. Min Act: -0.1700
Data Index: 1185261 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7355051 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2156. Min Act: -0.1700
Data Index: 4803823 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4656. Min Range: -5.4656
Max Act: 5.2156. Min Act: -0.1700
Data Index: 1956715 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19