Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2976 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.2743. Min Act: -0.1700
Data Index: 6729419 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.2431. Min Act: -0.1700
Data Index: 3375087 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.2431. Min Act: -0.1700
Data Index: 8318051 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.2118. Min Act: -0.1700
Data Index: 2164258 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.2118. Min Act: -0.1700
Data Index: 5466910 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.1806. Min Act: -0.1700
Data Index: 1065703 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.1493. Min Act: -0.1700
Data Index: 2657595 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.1181. Min Act: -0.1700
Data Index: 1691376 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.0868. Min Act: -0.1700
Data Index: 4713925 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.0556. Min Act: -0.1700
Data Index: 6629125 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2743. Min Range: -6.2743
Max Act: 6.0243. Min Act: -0.1700
Data Index: 1537568 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9618. Min Act: -0.1700
Data Index: 7803603 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9931. Min Act: -0.1700
Data Index: 8764005 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9306. Min Act: -0.1700
Data Index: 5593548 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9306. Min Act: -0.1700
Data Index: 6719898 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9306. Min Act: -0.1700
Data Index: 521887 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9306. Min Act: -0.1700
Data Index: 1036542 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9306. Min Act: -0.1700
Data Index: 4801245 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.8993. Min Act: -0.1700
Data Index: 5980398 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2743. Min Range: -6.2743
Max Act: 5.9306. Min Act: -0.1700
Data Index: 7742523 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19