Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4208 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.6934. Min Act: -0.1700
Data Index: 109422 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.5684. Min Act: -0.1700
Data Index: 7473771 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.5059. Min Act: -0.1700
Data Index: 8029377 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.4434. Min Act: -0.1700
Data Index: 6236285 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.4434. Min Act: -0.1700
Data Index: 1455259 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.3809. Min Act: -0.1700
Data Index: 8457235 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.3184. Min Act: -0.1700
Data Index: 4286726 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.1934. Min Act: -0.1700
Data Index: 8517704 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.0996. Min Act: -0.1700
Data Index: 3744602 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.0371. Min Act: -0.1700
Data Index: 6773792 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.0371. Min Act: -0.1700
Data Index: 1039589 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.0371. Min Act: -0.1700
Data Index: 3647434 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.0059. Min Act: -0.1700
Data Index: 7229112 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6934. Min Range: -7.6934
Max Act: 6.9746. Min Act: -0.1700
Data Index: 4028054 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6934. Min Range: -7.6934
Max Act: 7.0059. Min Act: -0.1700
Data Index: 5408159 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6934. Min Range: -7.6934
Max Act: 6.9434. Min Act: -0.1700
Data Index: 8367639 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6934. Min Range: -7.6934
Max Act: 6.9434. Min Act: -0.1700
Data Index: 2625533 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6934. Min Range: -7.6934
Max Act: 6.9121. Min Act: -0.1700
Data Index: 3385016 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6934. Min Range: -7.6934
Max Act: 6.9434. Min Act: -0.1700
Data Index: 7470970 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6934. Min Range: -7.6934
Max Act: 6.9121. Min Act: -0.1700
Data Index: 1233035 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19