Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5112 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.7670. Min Act: -0.1700
Data Index: 6273874 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.6108. Min Act: -0.1700
Data Index: 713529 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5795. Min Act: -0.1700
Data Index: 8529310 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5483. Min Act: -0.1700
Data Index: 5783383 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5483. Min Act: -0.1700
Data Index: 8259480 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5483. Min Act: -0.1700
Data Index: 1658807 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5170. Min Act: -0.1700
Data Index: 2217493 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5170. Min Act: -0.1700
Data Index: 1144526 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5170. Min Act: -0.1700
Data Index: 4105077 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.5170. Min Act: -0.1700
Data Index: 2607758 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4858. Min Act: -0.1700
Data Index: 1299311 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4545. Min Act: -0.1700
Data Index: 1638922 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4545. Min Act: -0.1700
Data Index: 4533849 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4545. Min Act: -0.1700
Data Index: 3247931 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4233. Min Act: -0.1700
Data Index: 1758302 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4233. Min Act: -0.1700
Data Index: 310103 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4233. Min Act: -0.1700
Data Index: 5037293 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4233. Min Act: -0.1700
Data Index: 101840 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4233. Min Act: -0.1700
Data Index: 5060148 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7670. Min Range: -5.7670
Max Act: 5.4233. Min Act: -0.1700
Data Index: 3984762 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19