Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2632 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.9263. Min Act: -0.1700
Data Index: 1204861 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.9576. Min Act: -0.1700
Data Index: 3582033 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8951. Min Act: -0.1700
Data Index: 4472261 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8951. Min Act: -0.1700
Data Index: 152992 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8638. Min Act: -0.1700
Data Index: 5024919 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8325. Min Act: -0.1700
Data Index: 4613196 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8325. Min Act: -0.1700
Data Index: 1797016 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8012. Min Act: -0.1700
Data Index: 760532 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8012. Min Act: -0.1700
Data Index: 467064 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7700. Min Act: -0.1700
Data Index: 2161008 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8012. Min Act: -0.1700
Data Index: 7265601 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7543. Min Act: -0.1700
Data Index: 3279491 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7700. Min Act: -0.1700
Data Index: 7622337 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.8012. Min Act: -0.1700
Data Index: 4921377 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7700. Min Act: -0.1700
Data Index: 2211201 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7543. Min Act: -0.1700
Data Index: 4225803 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7387. Min Act: -0.1700
Data Index: 7039163 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7074. Min Act: -0.1700
Data Index: 760533 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7074. Min Act: -0.1700
Data Index: 3015740 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9576. Min Range: -3.9576
Max Act: 3.7074. Min Act: -0.1700
Data Index: 2335692 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19