Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2496 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.2774. Min Act: -0.1700
Data Index: 2566088 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.2609. Min Act: -0.1700
Data Index: 374034 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.2444. Min Act: -0.1700
Data Index: 4356511 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.2113. Min Act: -0.1700
Data Index: 5957364 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.2113. Min Act: -0.1700
Data Index: 5215041 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.2113. Min Act: -0.1700
Data Index: 5259828 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1947. Min Act: -0.1700
Data Index: 5404205 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1947. Min Act: -0.1700
Data Index: 5140418 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1947. Min Act: -0.1700
Data Index: 544087 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1781. Min Act: -0.1700
Data Index: 938166 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1781. Min Act: -0.1700
Data Index: 2160532 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1614. Min Act: -0.1700
Data Index: 544084 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1781. Min Act: -0.1700
Data Index: 3009201 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1614. Min Act: -0.1700
Data Index: 6767545 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1614. Min Act: -0.1700
Data Index: 3925644 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1448. Min Act: -0.1700
Data Index: 7667998 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1281. Min Act: -0.1700
Data Index: 7771746 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1448. Min Act: -0.1700
Data Index: 1203989 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1448. Min Act: -0.1700
Data Index: 1266133 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2774. Min Range: -2.2774
Max Act: 2.1448. Min Act: -0.1700
Data Index: 3654672 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19