Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5105. Min Range: -7.5105
Max Act: 7.5105. Min Act: -0.1700
Data Index: 6709517 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5105. Min Range: -7.5105
Max Act: 7.0730. Min Act: -0.1700
Data Index: 8281565 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5105. Min Range: -7.5105
Max Act: 7.0418. Min Act: -0.1700
Data Index: 5340494 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.9793. Min Act: -0.1700
Data Index: 4479463 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.9480. Min Act: -0.1700
Data Index: 5175447 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.8543. Min Act: -0.1700
Data Index: 7115464 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.8230. Min Act: -0.1700
Data Index: 5584799 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7918. Min Act: -0.1700
Data Index: 65969 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7918. Min Act: -0.1700
Data Index: 4595481 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7918. Min Act: -0.1700
Data Index: 1237804 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7918. Min Act: -0.1700
Data Index: 2038447 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7605. Min Act: -0.1700
Data Index: 5315472 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7605. Min Act: -0.1700
Data Index: 1331936 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.6980. Min Act: -0.1700
Data Index: 5547927 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7293. Min Act: -0.1700
Data Index: 4767144 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.7293. Min Act: -0.1700
Data Index: 1686766 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.6980. Min Act: -0.1700
Data Index: 4219684 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.6980. Min Act: -0.1700
Data Index: 7850294 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.6980. Min Act: -0.1700
Data Index: 7691372 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5105. Min Range: -7.5105
Max Act: 6.6668. Min Act: -0.1700
Data Index: 8046302 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19