Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 570 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.3041. Min Act: -0.1700
Data Index: 6296222 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.2570. Min Act: -0.1700
Data Index: 3736756 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.2727. Min Act: -0.1700
Data Index: 1997978 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.2570. Min Act: -0.1700
Data Index: 3640003 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.2570. Min Act: -0.1700
Data Index: 7341801 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.2256. Min Act: -0.1700
Data Index: 3650186 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.2099. Min Act: -0.1700
Data Index: 6449454 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1784. Min Act: -0.1700
Data Index: 6311405 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1784. Min Act: -0.1700
Data Index: 5260316 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1784. Min Act: -0.1700
Data Index: 8342708 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1627. Min Act: -0.1700
Data Index: 5265893 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1627. Min Act: -0.1700
Data Index: 4573343 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1627. Min Act: -0.1700
Data Index: 7106323 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1469. Min Act: -0.1700
Data Index: 4849121 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1469. Min Act: -0.1700
Data Index: 2908317 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1469. Min Act: -0.1700
Data Index: 2433136 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1469. Min Act: -0.1700
Data Index: 272536 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1312. Min Act: -0.1700
Data Index: 7907601 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1312. Min Act: -0.1700
Data Index: 6229605 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3041. Min Range: -3.3041
Max Act: 3.1154. Min Act: -0.1700
Data Index: 3079961 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19