Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3984 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.7054. Min Act: -0.1700
Data Index: 392492 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.6741. Min Act: -0.1700
Data Index: 423461 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.6429. Min Act: -0.1700
Data Index: 1381045 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.6741. Min Act: -0.1700
Data Index: 1457914 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.5804. Min Act: -0.1700
Data Index: 4145998 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.5491. Min Act: -0.1700
Data Index: 41627 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.5179. Min Act: -0.1700
Data Index: 6874939 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4554. Min Act: -0.1700
Data Index: 5294199 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4866. Min Act: -0.1700
Data Index: 5968231 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4554. Min Act: -0.1700
Data Index: 4711760 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4866. Min Act: -0.1700
Data Index: 4415952 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4554. Min Act: -0.1700
Data Index: 1891354 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4554. Min Act: -0.1700
Data Index: 4075242 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4241. Min Act: -0.1700
Data Index: 4113234 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4241. Min Act: -0.1700
Data Index: 6367749 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.4241. Min Act: -0.1700
Data Index: 8399548 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.3929. Min Act: -0.1700
Data Index: 467249 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.3304. Min Act: -0.1700
Data Index: 7054867 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.3616. Min Act: -0.1700
Data Index: 5786719 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7054. Min Range: -4.7054
Max Act: 4.3616. Min Act: -0.1700
Data Index: 6286809 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19