Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 937 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.9543. Min Act: -0.1700
Data Index: 3225027 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.9543. Min Act: -0.1700
Data Index: 4729567 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2683059 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.8293. Min Act: -0.1700
Data Index: 6038942 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.7355. Min Act: -0.1700
Data Index: 2802144 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.7668. Min Act: -0.1700
Data Index: 7758602 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.7355. Min Act: -0.1700
Data Index: 8634519 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6730. Min Act: -0.1700
Data Index: 2734342 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6730. Min Act: -0.1700
Data Index: 5382381 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6730. Min Act: -0.1700
Data Index: 229592 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6730. Min Act: -0.1700
Data Index: 8018653 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6418. Min Act: -0.1700
Data Index: 2354592 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6418. Min Act: -0.1700
Data Index: 7566975 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6418. Min Act: -0.1700
Data Index: 1085025 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6105. Min Act: -0.1700
Data Index: 717160 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6105. Min Act: -0.1700
Data Index: 4357146 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6105. Min Act: -0.1700
Data Index: 2424424 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.6105. Min Act: -0.1700
Data Index: 6170567 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.5793. Min Act: -0.1700
Data Index: 7216331 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9543. Min Range: -5.9543
Max Act: 5.5793. Min Act: -0.1700
Data Index: 1637684 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19