Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1851 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3841. Min Range: -6.3841
Max Act: 6.3841. Min Act: -0.1700
Data Index: 1443061 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3841. Min Range: -6.3841
Max Act: 6.2279. Min Act: -0.1700
Data Index: 4930805 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3841. Min Range: -6.3841
Max Act: 6.0716. Min Act: -0.1700
Data Index: 7954916 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3841. Min Range: -6.3841
Max Act: 6.0404. Min Act: -0.1700
Data Index: 5430409 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3841. Min Range: -6.3841
Max Act: 6.0091. Min Act: -0.1700
Data Index: 5588287 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.9779. Min Act: -0.1700
Data Index: 7977066 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.8841. Min Act: -0.1700
Data Index: 7270945 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.8841. Min Act: -0.1700
Data Index: 2872798 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.8529. Min Act: -0.1700
Data Index: 5467372 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.8529. Min Act: -0.1700
Data Index: 5935361 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.8216. Min Act: -0.1700
Data Index: 3434249 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.7904. Min Act: -0.1700
Data Index: 53621 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.7904. Min Act: -0.1700
Data Index: 2492950 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.7904. Min Act: -0.1700
Data Index: 7604303 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.7591. Min Act: -0.1700
Data Index: 4010522 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.7591. Min Act: -0.1700
Data Index: 44558 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.7591. Min Act: -0.1700
Data Index: 3513612 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.6654. Min Act: -0.1700
Data Index: 193038 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.6966. Min Act: -0.1700
Data Index: 7706920 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3841. Min Range: -6.3841
Max Act: 5.6966. Min Act: -0.1700
Data Index: 225051 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19