Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4522 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.7321. Min Act: -0.1700
Data Index: 6201225 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.6696. Min Act: -0.1700
Data Index: 6201220 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.6383. Min Act: -0.1700
Data Index: 6201216 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.6226. Min Act: -0.1700
Data Index: 7476233 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5444. Min Act: -0.1700
Data Index: 6803189 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5287. Min Act: -0.1700
Data Index: 2637486 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5130. Min Act: -0.1700
Data Index: 5732819 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5444. Min Act: -0.1700
Data Index: 6201231 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5130. Min Act: -0.1700
Data Index: 6473826 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5287. Min Act: -0.1700
Data Index: 3247834 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5130. Min Act: -0.1700
Data Index: 4408678 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.5130. Min Act: -0.1700
Data Index: 6201222 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4974. Min Act: -0.1700
Data Index: 551695 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4974. Min Act: -0.1700
Data Index: 3025297 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4817. Min Act: -0.1700
Data Index: 7807078 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4817. Min Act: -0.1700
Data Index: 6847977 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4660. Min Act: -0.1700
Data Index: 5331279 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4660. Min Act: -0.1700
Data Index: 4564021 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4817. Min Act: -0.1700
Data Index: 5813461 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7321. Min Range: -3.7321
Max Act: 3.4660. Min Act: -0.1700
Data Index: 117187 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19