Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4857 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.3489. Min Act: -0.1700
Data Index: 3841033 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.3177. Min Act: -0.1700
Data Index: 5105424 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.2552. Min Act: -0.1700
Data Index: 5044722 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.2552. Min Act: -0.1700
Data Index: 3735187 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.2239. Min Act: -0.1700
Data Index: 7005388 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.1614. Min Act: -0.1700
Data Index: 6260760 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.1614. Min Act: -0.1700
Data Index: 8017020 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.0989. Min Act: -0.1700
Data Index: 4336387 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.0677. Min Act: -0.1700
Data Index: 4230031 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.0052. Min Act: -0.1700
Data Index: 5251799 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.0052. Min Act: -0.1700
Data Index: 1523572 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3489. Min Range: -7.3489
Max Act: 7.0052. Min Act: -0.1700
Data Index: 4373495 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.9739. Min Act: -0.1700
Data Index: 3023136 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.9739. Min Act: -0.1700
Data Index: 4872962 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.9427. Min Act: -0.1700
Data Index: 6049470 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.9114. Min Act: -0.1700
Data Index: 608116 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.8802. Min Act: -0.1700
Data Index: 3667772 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.8489. Min Act: -0.1700
Data Index: 3395120 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.8489. Min Act: -0.1700
Data Index: 3569666 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3489. Min Range: -7.3489
Max Act: 6.8489. Min Act: -0.1700
Data Index: 338417 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19