Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.6059. Min Act: -0.1700
Data Index: 8831700 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.5434. Min Act: -0.1700
Data Index: 3527056 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.5122. Min Act: -0.1700
Data Index: 2798994 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.4497. Min Act: -0.1700
Data Index: 3254834 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.4184. Min Act: -0.1700
Data Index: 6330509 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.4184. Min Act: -0.1700
Data Index: 2249773 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.4184. Min Act: -0.1700
Data Index: 5069473 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3872. Min Act: -0.1700
Data Index: 561449 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3872. Min Act: -0.1700
Data Index: 6092175 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3872. Min Act: -0.1700
Data Index: 3563344 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3872. Min Act: -0.1700
Data Index: 7795125 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3872. Min Act: -0.1700
Data Index: 7174711 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3559. Min Act: -0.1700
Data Index: 8773074 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3559. Min Act: -0.1700
Data Index: 8723428 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3559. Min Act: -0.1700
Data Index: 19308 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3559. Min Act: -0.1700
Data Index: 1918092 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3247. Min Act: -0.1700
Data Index: 1655843 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3247. Min Act: -0.1700
Data Index: 2563076 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3247. Min Act: -0.1700
Data Index: 2646546 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6059. Min Range: -4.6059
Max Act: 4.3247. Min Act: -0.1700
Data Index: 5320829 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19