Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.6152. Min Act: -0.1700
Data Index: 5818886 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.5527. Min Act: -0.1700
Data Index: 6650729 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.4902. Min Act: -0.1700
Data Index: 1408349 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.3964. Min Act: -0.1700
Data Index: 8318849 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.3964. Min Act: -0.1700
Data Index: 8457792 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.2402. Min Act: -0.1700
Data Index: 7054085 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.2402. Min Act: -0.1700
Data Index: 8494582 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.2089. Min Act: -0.1700
Data Index: 7927862 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.2089. Min Act: -0.1700
Data Index: 4203165 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.2089. Min Act: -0.1700
Data Index: 2850765 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1777. Min Act: -0.1700
Data Index: 8424723 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1777. Min Act: -0.1700
Data Index: 4698756 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1777. Min Act: -0.1700
Data Index: 622612 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1152. Min Act: -0.1700
Data Index: 8233130 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1464. Min Act: -0.1700
Data Index: 5533823 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1464. Min Act: -0.1700
Data Index: 8726639 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1152. Min Act: -0.1700
Data Index: 3710124 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1152. Min Act: -0.1700
Data Index: 6782547 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.1152. Min Act: -0.1700
Data Index: 2986987 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6152. Min Range: -7.6152
Max Act: 7.0839. Min Act: -0.1700
Data Index: 7915068 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19