Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1192 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.9796. Min Act: -0.1700
Data Index: 7794409 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.6983. Min Act: -0.1700
Data Index: 5572277 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.6671. Min Act: -0.1700
Data Index: 7812872 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.6046. Min Act: -0.1700
Data Index: 3228347 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.6046. Min Act: -0.1700
Data Index: 5804919 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.6046. Min Act: -0.1700
Data Index: 5572276 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.5421. Min Act: -0.1700
Data Index: 8583864 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4483. Min Act: -0.1700
Data Index: 196632 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4171. Min Act: -0.1700
Data Index: 3469239 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4483. Min Act: -0.1700
Data Index: 3116938 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4483. Min Act: -0.1700
Data Index: 7812873 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4171. Min Act: -0.1700
Data Index: 3469240 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4171. Min Act: -0.1700
Data Index: 2383617 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.4483. Min Act: -0.1700
Data Index: 5804918 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.3233. Min Act: -0.1700
Data Index: 325541 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.2608. Min Act: -0.1700
Data Index: 1368022 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.1671. Min Act: -0.1700
Data Index: 4054048 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.2608. Min Act: -0.1700
Data Index: 2153716 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.2296. Min Act: -0.1700
Data Index: 6640314 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9796. Min Range: -6.9796
Max Act: 6.1983. Min Act: -0.1700
Data Index: 7465472 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19