Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5049 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2921. Min Range: -4.2921
Max Act: 4.2921. Min Act: -0.1700
Data Index: 7043944 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2921. Min Range: -4.2921
Max Act: 4.0108. Min Act: -0.1700
Data Index: 3276375 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.9795. Min Act: -0.1700
Data Index: 6164030 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.9483. Min Act: -0.1700
Data Index: 5901029 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.9170. Min Act: -0.1700
Data Index: 7043945 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8857. Min Act: -0.1700
Data Index: 6220143 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8857. Min Act: -0.1700
Data Index: 8361786 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8857. Min Act: -0.1700
Data Index: 2727144 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8857. Min Act: -0.1700
Data Index: 176650 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8857. Min Act: -0.1700
Data Index: 8359701 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8857. Min Act: -0.1700
Data Index: 7749838 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8857. Min Act: -0.1700
Data Index: 594850 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8545. Min Act: -0.1700
Data Index: 3814821 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8545. Min Act: -0.1700
Data Index: 2792693 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8545. Min Act: -0.1700
Data Index: 4477303 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8232. Min Act: -0.1700
Data Index: 2727146 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8232. Min Act: -0.1700
Data Index: 960399 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8076. Min Act: -0.1700
Data Index: 2783240 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8076. Min Act: -0.1700
Data Index: 1481649 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2921. Min Range: -4.2921
Max Act: 3.8232. Min Act: -0.1700
Data Index: 2229583 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19