Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5303 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.8684. Min Act: -0.1700
Data Index: 6342999 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.6338. Min Act: -0.1700
Data Index: 4280597 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.6182. Min Act: -0.1700
Data Index: 7554154 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.5869. Min Act: -0.1700
Data Index: 8697118 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.5399. Min Act: -0.1700
Data Index: 7236121 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4929. Min Act: -0.1700
Data Index: 2237438 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4616. Min Act: -0.1700
Data Index: 7325153 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4459. Min Act: -0.1700
Data Index: 8718317 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4459. Min Act: -0.1700
Data Index: 8012047 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4616. Min Act: -0.1700
Data Index: 6480157 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4303. Min Act: -0.1700
Data Index: 6079424 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4303. Min Act: -0.1700
Data Index: 8259826 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4303. Min Act: -0.1700
Data Index: 2221560 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4303. Min Act: -0.1700
Data Index: 4709894 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4146. Min Act: -0.1700
Data Index: 902925 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4146. Min Act: -0.1700
Data Index: 7713024 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4146. Min Act: -0.1700
Data Index: 4256032 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4146. Min Act: -0.1700
Data Index: 5141423 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.4146. Min Act: -0.1700
Data Index: 1487564 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8684. Min Range: -3.8684
Max Act: 3.3832. Min Act: -0.1700
Data Index: 6896618 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19