Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5135 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1232. Min Range: -5.1232
Max Act: 5.1232. Min Act: -0.1700
Data Index: 6585130 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1232. Min Range: -5.1232
Max Act: 5.0607. Min Act: -0.1700
Data Index: 39202 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1232. Min Range: -5.1232
Max Act: 5.0295. Min Act: -0.1700
Data Index: 6585134 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.9982. Min Act: -0.1700
Data Index: 4622569 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.9982. Min Act: -0.1700
Data Index: 727441 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.9670. Min Act: -0.1700
Data Index: 4575022 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.9670. Min Act: -0.1700
Data Index: 5066343 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.9357. Min Act: -0.1700
Data Index: 2302268 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.9045. Min Act: -0.1700
Data Index: 2302272 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.9045. Min Act: -0.1700
Data Index: 1723762 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8732. Min Act: -0.1700
Data Index: 3367754 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8732. Min Act: -0.1700
Data Index: 5497411 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8732. Min Act: -0.1700
Data Index: 1843808 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8732. Min Act: -0.1700
Data Index: 7661766 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8732. Min Act: -0.1700
Data Index: 7770110 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8732. Min Act: -0.1700
Data Index: 3298181 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8732. Min Act: -0.1700
Data Index: 8594168 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8107. Min Act: -0.1700
Data Index: 5781152 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8420. Min Act: -0.1700
Data Index: 3230667 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1232. Min Range: -5.1232
Max Act: 4.8420. Min Act: -0.1700
Data Index: 5620102 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19