Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.6171. Min Act: -0.1700
Data Index: 3714800 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.4608. Min Act: -0.1700
Data Index: 2275281 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.4921. Min Act: -0.1700
Data Index: 1576214 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.4608. Min Act: -0.1700
Data Index: 2162136 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.4608. Min Act: -0.1700
Data Index: 7508006 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3983. Min Act: -0.1700
Data Index: 314434 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.4296. Min Act: -0.1700
Data Index: 2010803 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.4296. Min Act: -0.1700
Data Index: 4708530 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.4608. Min Act: -0.1700
Data Index: 4733188 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3983. Min Act: -0.1700
Data Index: 6775471 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3671. Min Act: -0.1700
Data Index: 7909826 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3671. Min Act: -0.1700
Data Index: 8655402 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2050826 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3046. Min Act: -0.1700
Data Index: 1926624 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3358. Min Act: -0.1700
Data Index: 510586 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3671. Min Act: -0.1700
Data Index: 2390289 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.2733. Min Act: -0.1700
Data Index: 2775624 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3358. Min Act: -0.1700
Data Index: 390329 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.2733. Min Act: -0.1700
Data Index: 8296014 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6171. Min Range: -4.6171
Max Act: 4.3046. Min Act: -0.1700
Data Index: 8672794 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19