Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2298 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.7838. Min Act: -0.1700
Data Index: 3233680 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.6275. Min Act: -0.1700
Data Index: 7647338 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.6275. Min Act: -0.1700
Data Index: 3929111 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.5963. Min Act: -0.1700
Data Index: 664821 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.5338. Min Act: -0.1700
Data Index: 1937402 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.5338. Min Act: -0.1700
Data Index: 5651549 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.5650. Min Act: -0.1700
Data Index: 3709084 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.5025. Min Act: -0.1700
Data Index: 903356 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.5025. Min Act: -0.1700
Data Index: 1888072 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4713. Min Act: -0.1700
Data Index: 4282302 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4713. Min Act: -0.1700
Data Index: 2193046 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4713. Min Act: -0.1692
Data Index: 1045363 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4713. Min Act: -0.1700
Data Index: 402166 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4713. Min Act: -0.1700
Data Index: 2526274 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4400. Min Act: -0.1700
Data Index: 510523 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4400. Min Act: -0.1700
Data Index: 1769395 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4400. Min Act: -0.1700
Data Index: 4497125 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4088. Min Act: -0.1699
Data Index: 4886075 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4400. Min Act: -0.1700
Data Index: 5375782 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7838. Min Range: -5.7838
Max Act: 5.4713. Min Act: -0.1700
Data Index: 3186028 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19