Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5374 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0043. Min Range: -2.0043
Max Act: 2.0043. Min Act: -0.1700
Data Index: 3553367 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9704. Min Act: -0.1700
Data Index: 7936412 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9365. Min Act: -0.1700
Data Index: 359602 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9365. Min Act: -0.1700
Data Index: 2519644 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9195. Min Act: -0.1700
Data Index: 498755 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9110. Min Act: -0.1700
Data Index: 4644784 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9195. Min Act: -0.1700
Data Index: 966219 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9024. Min Act: -0.1700
Data Index: 4179051 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.9110. Min Act: -0.1700
Data Index: 8044341 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8768. Min Act: -0.1700
Data Index: 8120562 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8768. Min Act: -0.1700
Data Index: 5112908 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8768. Min Act: -0.1700
Data Index: 2026867 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8683. Min Act: -0.1700
Data Index: 1749066 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8768. Min Act: -0.1700
Data Index: 1284187 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8768. Min Act: -0.1700
Data Index: 3880171 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8854. Min Act: -0.1699
Data Index: 4320604 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8597. Min Act: -0.1700
Data Index: 2191459 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8683. Min Act: -0.1700
Data Index: 6151618 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8683. Min Act: -0.1700
Data Index: 1286502 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0043. Min Range: -2.0043
Max Act: 1.8597. Min Act: -0.1700
Data Index: 6545801 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19