Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.4249. Min Act: -0.1700
Data Index: 8548542 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.3624. Min Act: -0.1700
Data Index: 412742 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.3624. Min Act: -0.1700
Data Index: 8548544 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.3624. Min Act: -0.1700
Data Index: 8548545 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.3311. Min Act: -0.1700
Data Index: 7364217 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.3311. Min Act: -0.1700
Data Index: 4793127 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2686. Min Act: -0.1700
Data Index: 8548549 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2686. Min Act: -0.1700
Data Index: 8548548 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2374. Min Act: -0.1700
Data Index: 1258614 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2686. Min Act: -0.1700
Data Index: 2506824 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2686. Min Act: -0.1700
Data Index: 3926563 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2061. Min Act: -0.1700
Data Index: 6453850 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2374. Min Act: -0.1700
Data Index: 202815 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2374. Min Act: -0.1700
Data Index: 3202300 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2374. Min Act: -0.1700
Data Index: 2196634 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2061. Min Act: -0.1700
Data Index: 7631043 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2374. Min Act: -0.1700
Data Index: 8089158 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2374. Min Act: -0.1700
Data Index: 8548543 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.2061. Min Act: -0.1700
Data Index: 4842879 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4249. Min Range: -5.4249
Max Act: 5.1749. Min Act: -0.1700
Data Index: 3722986 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19