Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 987 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1592. Min Range: -5.1592
Max Act: 5.1592. Min Act: -0.1700
Data Index: 2370652 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1592. Min Range: -5.1592
Max Act: 5.1280. Min Act: -0.1700
Data Index: 1732064 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1592. Min Range: -5.1592
Max Act: 5.1280. Min Act: -0.1700
Data Index: 406286 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1592. Min Range: -5.1592
Max Act: 5.0655. Min Act: -0.1700
Data Index: 5598196 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1592. Min Range: -5.1592
Max Act: 5.0342. Min Act: -0.1700
Data Index: 2604167 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1592. Min Range: -5.1592
Max Act: 5.0030. Min Act: -0.1700
Data Index: 5079685 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.9092. Min Act: -0.1700
Data Index: 6177537 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.9092. Min Act: -0.1700
Data Index: 902276 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.9092. Min Act: -0.1700
Data Index: 8068234 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8780. Min Act: -0.1700
Data Index: 5328448 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8780. Min Act: -0.1700
Data Index: 7423186 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8780. Min Act: -0.1700
Data Index: 2478551 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8780. Min Act: -0.1700
Data Index: 4680688 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8780. Min Act: -0.1700
Data Index: 742225 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8467. Min Act: -0.1700
Data Index: 3254705 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8467. Min Act: -0.1700
Data Index: 4610203 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8467. Min Act: -0.1700
Data Index: 7423184 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8467. Min Act: -0.1700
Data Index: 5864945 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8155. Min Act: -0.1700
Data Index: 1951435 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1592. Min Range: -5.1592
Max Act: 4.8155. Min Act: -0.1700
Data Index: 7395247 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19