Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.8161. Min Act: -0.1700
Data Index: 3209941 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 6143397 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 5623237 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 7006928 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5974. Min Act: -0.1700
Data Index: 4968533 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 3194013 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5661. Min Act: -0.1700
Data Index: 8184497 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 5623238 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 4837853 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5349. Min Act: -0.1700
Data Index: 7006933 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5036. Min Act: -0.1700
Data Index: 3356416 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.5036. Min Act: -0.1700
Data Index: 5801922 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4411. Min Act: -0.1700
Data Index: 5320698 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4724. Min Act: -0.1700
Data Index: 7006927 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4411. Min Act: -0.1700
Data Index: 3209940 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4411. Min Act: -0.1700
Data Index: 5623240 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4099. Min Act: -0.1700
Data Index: 2504001 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4099. Min Act: -0.1700
Data Index: 5942932 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.3786. Min Act: -0.1700
Data Index: 2503999 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8161. Min Range: -5.8161
Max Act: 5.4099. Min Act: -0.1700
Data Index: 4520543 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19