Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.8682. Min Act: -0.1700
Data Index: 1982646 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.7119. Min Act: -0.1700
Data Index: 8626339 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.7744. Min Act: -0.1700
Data Index: 6961231 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.7119. Min Act: -0.1700
Data Index: 47361 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.7119. Min Act: -0.1700
Data Index: 5279394 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.6494. Min Act: -0.1700
Data Index: 5014987 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.6807. Min Act: -0.1700
Data Index: 5739051 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.6182. Min Act: -0.1700
Data Index: 4069729 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.5869. Min Act: -0.1700
Data Index: 4579737 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.5557. Min Act: -0.1700
Data Index: 3383037 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.4932. Min Act: -0.1700
Data Index: 4502425 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.4932. Min Act: -0.1700
Data Index: 976347 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.4932. Min Act: -0.1700
Data Index: 8443192 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.4307. Min Act: -0.1700
Data Index: 5582257 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.4619. Min Act: -0.1700
Data Index: 7900678 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.4619. Min Act: -0.1700
Data Index: 6404330 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.3994. Min Act: -0.1700
Data Index: 8045000 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.4307. Min Act: -0.1700
Data Index: 5630263 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.3369. Min Act: -0.1700
Data Index: 4502267 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8682. Min Range: -6.8682
Max Act: 6.3057. Min Act: -0.1700
Data Index: 4905570 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19