Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3931. Min Act: -0.1700
Data Index: 1915384 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3775. Min Act: -0.1700
Data Index: 7226496 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3931. Min Act: -0.1700
Data Index: 8069189 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3618. Min Act: -0.1700
Data Index: 1950255 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3461. Min Act: -0.1700
Data Index: 6247313 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3775. Min Act: -0.1700
Data Index: 7430392 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3461. Min Act: -0.1700
Data Index: 57360 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3461. Min Act: -0.1700
Data Index: 4356959 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3618. Min Act: -0.1700
Data Index: 5876085 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2833. Min Act: -0.1700
Data Index: 4809127 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3147. Min Act: -0.1700
Data Index: 6317341 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3304. Min Act: -0.1700
Data Index: 2437207 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.3304. Min Act: -0.1700
Data Index: 6550955 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2990. Min Act: -0.1700
Data Index: 6458998 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2519. Min Act: -0.1700
Data Index: 8342169 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2362. Min Act: -0.1700
Data Index: 1466160 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1576. Min Act: -0.1700
Data Index: 4528515 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2047. Min Act: -0.1700
Data Index: 3879368 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.1890. Min Act: -0.1700
Data Index: 7566620 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3931. Min Range: -3.3931
Max Act: 3.2205. Min Act: -0.1700
Data Index: 1884408 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19