Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1031 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.9467. Min Act: -0.1700
Data Index: 4047098 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8956. Min Act: -0.1700
Data Index: 2861127 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8956. Min Act: -0.1700
Data Index: 6990746 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8871. Min Act: -0.1700
Data Index: 2837787 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8700. Min Act: -0.1700
Data Index: 3913034 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8615. Min Act: -0.1700
Data Index: 76704 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8700. Min Act: -0.1700
Data Index: 1220911 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8700. Min Act: -0.1700
Data Index: 5527723 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8358. Min Act: -0.1700
Data Index: 4447602 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8529. Min Act: -0.1700
Data Index: 5057150 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8443. Min Act: -0.1700
Data Index: 4262793 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8615. Min Act: -0.1700
Data Index: 3683746 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8443. Min Act: -0.1700
Data Index: 3379788 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8358. Min Act: -0.1700
Data Index: 7127453 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8358. Min Act: -0.1700
Data Index: 2107668 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8358. Min Act: -0.1700
Data Index: 7687945 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8358. Min Act: -0.1700
Data Index: 5858895 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8186. Min Act: -0.1700
Data Index: 522518 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8272. Min Act: -0.1700
Data Index: 6975614 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9467. Min Range: -1.9467
Max Act: 1.8186. Min Act: -0.1700
Data Index: 1071007 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19