Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3677. Min Range: -9.3677
Max Act: 9.3677. Min Act: -0.1700
Data Index: 8665181 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3677. Min Range: -9.3677
Max Act: 9.3052. Min Act: -0.1700
Data Index: 2211360 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3677. Min Range: -9.3677
Max Act: 9.1177. Min Act: -0.1700
Data Index: 5464903 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3677. Min Range: -9.3677
Max Act: 9.0552. Min Act: -0.1700
Data Index: 3690976 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3677. Min Range: -9.3677
Max Act: 9.0552. Min Act: -0.1700
Data Index: 1933914 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.9927. Min Act: -0.1700
Data Index: 2998990 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.9927. Min Act: -0.1700
Data Index: 7462021 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.8677. Min Act: -0.1700
Data Index: 1441963 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.8677. Min Act: -0.1700
Data Index: 2080808 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.7427. Min Act: -0.1700
Data Index: 6766320 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.8052. Min Act: -0.1700
Data Index: 5409363 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.8052. Min Act: -0.1700
Data Index: 4143820 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.8052. Min Act: -0.1700
Data Index: 1286022 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.7427. Min Act: -0.1700
Data Index: 3454520 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.6802. Min Act: -0.1700
Data Index: 5879819 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.6802. Min Act: -0.1700
Data Index: 4255490 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.6177. Min Act: -0.1700
Data Index: 3860288 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.6177. Min Act: -0.1700
Data Index: 7361961 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.6802. Min Act: -0.1700
Data Index: 5195162 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3677. Min Range: -9.3677
Max Act: 8.6177. Min Act: -0.1700
Data Index: 2397580 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19