Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.7559. Min Act: -0.1700
Data Index: 7264677 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.6309. Min Act: -0.1700
Data Index: 4664432 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.5059. Min Act: -0.1700
Data Index: 8575251 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.5059. Min Act: -0.1700
Data Index: 8623030 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.4434. Min Act: -0.1700
Data Index: 3997429 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.4747. Min Act: -0.1700
Data Index: 3633174 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.5059. Min Act: -0.1700
Data Index: 7059689 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.4434. Min Act: -0.1700
Data Index: 2081881 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3809. Min Act: -0.1700
Data Index: 6360686 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3809. Min Act: -0.1700
Data Index: 8092555 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3497. Min Act: -0.1700
Data Index: 3982850 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3497. Min Act: -0.1700
Data Index: 2712962 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3497. Min Act: -0.1700
Data Index: 7264678 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3497. Min Act: -0.1700
Data Index: 564439 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3497. Min Act: -0.1700
Data Index: 5796023 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.2872. Min Act: -0.1700
Data Index: 4326160 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3184. Min Act: -0.1700
Data Index: 1588842 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3184. Min Act: -0.1700
Data Index: 7335347 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.2872. Min Act: -0.1700
Data Index: 7905934 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7559. Min Range: -5.7559
Max Act: 5.3184. Min Act: -0.1700
Data Index: 3225166 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19