Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0105. Min Range: -7.0105
Max Act: 7.0105. Min Act: -0.1700
Data Index: 6796666 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.8543. Min Act: -0.1700
Data Index: 5807427 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.8543. Min Act: -0.1700
Data Index: 8309368 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.8855. Min Act: -0.1700
Data Index: 6273116 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.8230. Min Act: -0.1700
Data Index: 5074859 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.7293. Min Act: -0.1700
Data Index: 4903490 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.7605. Min Act: -0.1700
Data Index: 7239724 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.5730. Min Act: -0.1700
Data Index: 5459766 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.4480. Min Act: -0.1700
Data Index: 4098878 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.5105. Min Act: -0.1700
Data Index: 5109754 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.4793. Min Act: -0.1700
Data Index: 106793 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.4168. Min Act: -0.1700
Data Index: 8507267 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.4480. Min Act: -0.1700
Data Index: 6981900 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.4480. Min Act: -0.1700
Data Index: 6628637 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.4168. Min Act: -0.1700
Data Index: 2292097 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.4168. Min Act: -0.1700
Data Index: 3903270 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.3855. Min Act: -0.1700
Data Index: 7574496 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2853599 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.3543. Min Act: -0.1700
Data Index: 4861736 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0105. Min Range: -7.0105
Max Act: 6.3230. Min Act: -0.1700
Data Index: 631648 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19