Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1128 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.8134. Min Act: -0.1700
Data Index: 56834 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.7197. Min Act: -0.1700
Data Index: 3957022 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.5947. Min Act: -0.1700
Data Index: 654736 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.5322. Min Act: -0.1700
Data Index: 8192912 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.5322. Min Act: -0.1700
Data Index: 906881 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.5322. Min Act: -0.1700
Data Index: 6192483 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.5322. Min Act: -0.1700
Data Index: 3966104 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.5009. Min Act: -0.1700
Data Index: 6873550 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4697. Min Act: -0.1700
Data Index: 4293600 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4697. Min Act: -0.1700
Data Index: 3150376 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4697. Min Act: -0.1700
Data Index: 6972934 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4697. Min Act: -0.1700
Data Index: 1854238 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4384. Min Act: -0.1700
Data Index: 3448675 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4384. Min Act: -0.1700
Data Index: 403944 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4384. Min Act: -0.1700
Data Index: 3619555 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4072. Min Act: -0.1700
Data Index: 1854242 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4072. Min Act: -0.1700
Data Index: 693295 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4072. Min Act: -0.1700
Data Index: 3037327 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4072. Min Act: -0.1700
Data Index: 8611178 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8134. Min Range: -5.8134
Max Act: 5.4072. Min Act: -0.1700
Data Index: 4293602 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19