Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5296 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.8994. Min Act: -0.1700
Data Index: 3555157 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.7432. Min Act: -0.1700
Data Index: 7797195 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.6182. Min Act: -0.1700
Data Index: 4854192 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.5869. Min Act: -0.1700
Data Index: 6747115 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.5557. Min Act: -0.1700
Data Index: 5105164 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.4619. Min Act: -0.1700
Data Index: 3309196 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3994. Min Act: -0.1700
Data Index: 1648258 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3682. Min Act: -0.1700
Data Index: 3962325 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3682. Min Act: -0.1700
Data Index: 6409506 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3682. Min Act: -0.1700
Data Index: 4920243 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3369. Min Act: -0.1700
Data Index: 2659569 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3369. Min Act: -0.1700
Data Index: 2871068 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3057. Min Act: -0.1700
Data Index: 5261020 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.3057. Min Act: -0.1700
Data Index: 677126 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.2744. Min Act: -0.1700
Data Index: 870797 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.2744. Min Act: -0.1700
Data Index: 8139722 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.2744. Min Act: -0.1700
Data Index: 5761637 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.2432. Min Act: -0.1700
Data Index: 4308604 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.2119. Min Act: -0.1700
Data Index: 7684237 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8994. Min Range: -7.8994
Max Act: 7.2119. Min Act: -0.1700
Data Index: 1103616 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19