Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3682. Min Range: -9.3682
Max Act: 9.3682. Min Act: -0.1700
Data Index: 6750250 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3682. Min Range: -9.3682
Max Act: 9.2432. Min Act: -0.1700
Data Index: 2641756 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3682. Min Range: -9.3682
Max Act: 9.1182. Min Act: -0.1700
Data Index: 2263297 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3682. Min Range: -9.3682
Max Act: 9.1182. Min Act: -0.1700
Data Index: 8634327 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3682. Min Range: -9.3682
Max Act: 9.1182. Min Act: -0.1700
Data Index: 3899002 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3682. Min Range: -9.3682
Max Act: 9.0557. Min Act: -0.1700
Data Index: 4381325 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9932. Min Act: -0.1700
Data Index: 7953164 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9932. Min Act: -0.1700
Data Index: 578714 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9307. Min Act: -0.1700
Data Index: 7884844 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9307. Min Act: -0.1700
Data Index: 6454250 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9307. Min Act: -0.1700
Data Index: 8041405 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9307. Min Act: -0.1700
Data Index: 5832312 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9307. Min Act: -0.1700
Data Index: 5234514 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.9307. Min Act: -0.1700
Data Index: 7416820 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.8057. Min Act: -0.1700
Data Index: 5932050 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.8057. Min Act: -0.1700
Data Index: 5699962 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.8057. Min Act: -0.1700
Data Index: 7822461 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.8057. Min Act: -0.1700
Data Index: 3987427 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.7432. Min Act: -0.1700
Data Index: 825601 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3682. Min Range: -9.3682
Max Act: 8.7432. Min Act: -0.1700
Data Index: 5291359 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19