Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.2084. Min Act: -0.1700
Data Index: 1361054 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.2084. Min Act: -0.1695
Data Index: 1015877 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1835. Min Act: -0.1700
Data Index: 1432874 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1752. Min Act: -0.1700
Data Index: 8034219 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1585. Min Act: -0.1700
Data Index: 2808493 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1585. Min Act: -0.1700
Data Index: 3718216 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1585. Min Act: -0.1700
Data Index: 2294018 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1419. Min Act: -0.1700
Data Index: 6572818 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1335. Min Act: -0.1700
Data Index: 6463873 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1168. Min Act: -0.1700
Data Index: 5623405 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1168. Min Act: -0.1700
Data Index: 5292363 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1084. Min Act: -0.1700
Data Index: 914607 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1168. Min Act: -0.1700
Data Index: 8292492 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.0917. Min Act: -0.1700
Data Index: 155622 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.1084. Min Act: -0.1700
Data Index: 7463114 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.0917. Min Act: -0.1700
Data Index: 8781075 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.0833. Min Act: -0.1700
Data Index: 3390207 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.0749. Min Act: -0.1700
Data Index: 6964000 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.0833. Min Act: -0.1700
Data Index: 3536765 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2084. Min Range: -2.2084
Max Act: 2.0917. Min Act: -0.1699
Data Index: 8183282 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19